Anti-blocking optimized pneumatic conveying intelligent control method and system

Abstract

The invention discloses an anti-blocking optimization pneumatic conveying intelligent control method and system, and the method comprises the steps: enabling the system to receive a starting instruction, initializing system parameters, and entering a standby state; the system enters a conveying state, the opening degree of the valve is calculated according to initialized system parameters, and meanwhile pressure data and flow data are collected in real time and stored in a storage; after the transmission process is finished, feature extraction is carried out on the collected data, and historical trend parameters are stored; dividing the conveying state into a normal state, an early warning state and a blockage critical state, selecting key operation variables influencing blockage from system parameters, processing the key operation variables to form a blockage risk scoring model so as to obtain a risk score, judging the current conveying state of the system, and executing corresponding measures; when the number of times of conveying reaches the preset number of times, the system conducts conveying optimization according to the pipe blocking rate and executes in the follow-up conveying process, and the system has the advantage that the conveying process can be accurately monitored and intelligently optimized.

Description

Technical Field

[0001] The present application relates to the technical field of pneumatic conveying, and in particular to an intelligent control method and system for anti-blocking and optimized pneumatic conveying. Background Art

[0002] Pneumatic conveying, also known as air flow conveying, utilizes the energy of air flow to transport granular materials along the direction of air flow in a closed pipe. It is a specific application of fluidization technology. The pneumatic conveying device has a simple structure and is easy to operate. It can be used for horizontal, vertical or inclined conveying. During the conveying process, physical operations such as heating, cooling, drying and air flow classification of materials or certain chemical operations can also be carried out simultaneously. As an efficient material conveying technology, pneumatic conveying systems are widely used in chemical industry, metallurgy, building materials and other fields.

[0003] However, the existing pneumatic conveying system has the following defects: in actual operation, pipeline blockage is always a key bottleneck restricting its stability and efficiency. Existing anti-blocking methods mostly rely on single parameter monitoring or manual intervention, which is difficult to meet the intelligent and real-time requirements under complex working conditions. Summary of the Invention

[0004] One purpose of the present application is to provide an intelligent control method and system for pneumatic conveying with anti-blocking optimization that can accurately monitor and intelligently optimize the conveying process.

[0005] To achieve the above objectives, the technical solution adopted in this application is: an intelligent control method for anti-blocking and optimized pneumatic conveying, comprising the following steps: S100: The system receives a start command, the control unit enters a preparation mode, activates the sensor module, and initializes system parameters including the standard delivery pressure value, the standard delivery flow value, the abnormal delivery pressure change rate, the abnormal delivery flow change rate, the delivery time dimension variable, and the historical trend parameter. After the initialization is completed, the system enters a standby state; S200, the system enters the delivery state, the control unit calculates the valve opening corresponding to the standard delivery flow according to the initialized system parameters, and the system starts to collect pressure data and flow data in real time and store them in the memory; S300, after the conveying process is completed, the system extracts features from the collected data and stores them in historical trend parameters; S400: Create a multi-parameter combination rule to classify the transport state into a normal state, a warning state, and a critical congestion state. Select key operating variables that affect congestion during the transport process from the system parameters. Process these key operating variables to form a congestion risk scoring model. Determine the risk score based on the congestion risk scoring model, determine the current transport state of the system, and then cause the system to take appropriate measures. S500: When the number of transports reaches the preset number, the system optimizes the initialized system parameters and the judgment conditions of each transport state according to the pipe blockage rate. During the subsequent transport process, the system performs a pipe blockage warning based on the new system parameters and the judgment conditions of the transport state.

[0006] In some embodiments, key operating variables include pressure, flow, pressure change rate, flow change rate and abnormal duration. The key operating variables are converted into key factors to obtain the degree of deviation between the current pressure and the standard pressure, the degree of deviation between the current flow and the standard flow, whether the change rate of pressure and flow exceeds the abnormal state threshold, and whether the delivery time exceeds the normal range, and the key factors are normalized.

[0007] In some embodiments, the key factors are normalized to the interval [0,1]. The system assigns different weights to each key factor according to its sensitivity to the congestion trend, constructs a weighted scoring model, and makes the resulting risk score fall within the range [0,1]. The two values ​​in [0,1] are set as x and y. When the risk score is [0,x), it is judged as low risk, when the risk score is [x,y], it is judged as medium risk, and when the risk score is (y,1], it is judged as high risk. The risk score calculation formula is: risk score = w1×P_norm+w2×Q_norm+w3×dP / dt_norm+w4×dQ / dt_norm+w5×Δt_norm, where w1, w2, w3, w4, and w5 are weight values, P is pressure, Q is flow, dP / dt is the pressure change rate, dQ / dt is the flow change rate, and Δt is the abnormality duration. The initialized system parameters are manually input for the first time, and are subsequently dynamically and automatically updated by the system according to the optimization rules.

[0008] In some embodiments, the multi-parameter combination rule for the normal state includes: a first condition that the maximum delivery pressure is equal to or lower than 90% of the standard delivery pressure; a second condition that the minimum delivery flow rate is equal to or higher than 120% of the standard delivery flow rate; and a third condition that the delivery time dimension variable is within a normal range. If the above conditions are met, the system determines that the state is normal. The parameter combination rules for the warning state include: the first condition, the maximum delivery pressure is between 90% and 120% of the standard delivery pressure; the second condition, the minimum delivery flow rate is between 100% and 120% of the standard delivery flow rate; the third condition, the pressure change rate or flow change rate exceeds 90% of the abnormal delivery change rate; the third condition, the delivery time dimension variable is abnormal. If any of the above conditions are met, the system will be judged as a warning state; The parameter combination rules for the critical blockage state include: the first condition, the maximum delivery pressure reaches or exceeds 120% of the standard delivery pressure; the second condition, the minimum delivery flow rate drops below 100% of the standard delivery flow rate; the third condition, the pressure change rate or flow change rate exceeds 90% of the abnormal delivery change rate; the third condition, the delivery time dimension variable continues to be abnormal. If any of the above conditions is met, the system will determine it as a critical blockage state.

[0009] In some embodiments, the system calculates the actual filling rate of 60%-80% of the feed volume divided by the output of the system, which is suitable for obtaining the normal range of the delivery time. If the delivery time dimension variable is outside the normal range, it is judged as abnormal delivery behavior. If it exceeds 1.2 times the normal range of the delivery time dimension variable, it is judged as a continuous abnormality.

[0010] In some embodiments, the historical trend parameters are suitable for recording a first feature, a second feature, and a third feature: the first feature is the maximum pressure and the minimum flow during the delivery process; the second feature is filtering the pressure data and flow data using a fixed sliding time window, and calculating the maximum pressure change rate in the rising phase of delivery and the maximum flow change rate in the falling phase; the third feature is statistically analyzing the longest time period in which the pressure exceeds the standard delivery pressure value and continues to rise during the delivery process, and recording whether blockage occurs; the sliding time window ranges from 10 to 60 seconds.

[0011] In some embodiments, when the number of deliveries reaches 50 times and the pipe blockage rate is less than 10%, the system corrects the prediction results of the historical trend parameters for the critical state of blockage and optimizes the initialized system parameters; when the number of deliveries reaches 50 times and the pipe blockage rate is not less than 10%, the system further compares the prediction results of the historical trend parameters with the actual pipe blockage situation and adjusts the initialized system parameters.

[0012] In some embodiments, the number of delivery times preset by the system is set as the initial delivery stage. In the initial delivery stage, the system only makes predictions based on strategies and does not perform pipe blockage warnings. The prediction results are stored in historical trend parameters.

[0013] In some embodiments, the content of the historical trend parameter is empty when initialized; during the system transportation process, the sensor module collects pressure data and flow data in the pipeline at a fixed frequency of 1-5 seconds.

[0014] A pneumatic conveying system applies any of the above-mentioned anti-blocking and optimized pneumatic conveying intelligent control methods.

[0015] Compared with the existing technology, the beneficial effect of the present application is that the anti-blocking optimized pneumatic conveying intelligent control method and system of the present application is aimed at solving the blockage problem in the pneumatic conveying system. Its core principle is to combine real-time parameters (pressure P, flow Q, pressure change rate dP / dt, flow change rate dQ / dt) with time dimension variables (abnormal duration Δt and historical trend parameter H_trend) to construct intelligent judgment rules, which solves the problems of early warning lag of blockage, high misjudgment rate of single parameter monitoring, lack of adaptability, slow response speed of anti-blocking measures and insufficient long-term operation stability, and realizes early warning of blockage, accurate detection, judgment and rapid optimization control of the conveying process. DETAILED DESCRIPTION

[0016] Below, the present application is further described in conjunction with specific implementation methods. It should be noted that, under the premise of no conflict, the various embodiments or technical features described below can be arbitrarily combined to form new embodiments.

[0017] It should be noted that the terms "first", "second", etc. in the description and claims of this application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0018] The terms "comprises" and "having" and any variations thereof in the specification and claims of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus that includes a series of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, product or apparatus.

[0019] The following is a further description of this application: The traditional pneumatic conveying system has the following specific problems: the early warning of blockage is relatively delayed. The traditional method usually only issues an alarm when the pressure or flow reaches the limit value, resulting in a delayed blockage warning and missing the best time for intervention. In addition, since only a single parameter such as pressure or flow is detected to determine blockage, it is easily affected by instantaneous fluctuations or noise interference, and the monitoring misjudgment rate is high.

[0020] Traditional pneumatic conveying systems also lack the ability to adaptively respond to different materials and working conditions. Different materials (such as powders and particles) and conveying conditions (such as pipeline length and airflow velocity) have significantly different effects on blockage characteristics. Traditional fixed threshold methods are difficult to adapt to diverse scenarios.

[0021] Traditional pneumatic conveying systems also have the problem of slow response speed of anti-blocking measures. After detecting the risk of blockage, the existing system often requires manual intervention or simple adjustments, and the response speed is not fast enough to prevent blockage from occurring.

[0022] In addition, the long-term operating stability of traditional pneumatic conveying systems is insufficient. Traditional methods lack analysis of the long-term operating trends of the system, making it difficult to predict potential blockage points, resulting in decreased stability.

[0023] In order to solve the defects of the above-mentioned traditional pneumatic conveying system, the present application provides an anti-blocking and optimized pneumatic conveying intelligent control method, which includes the following steps.

[0024] S100, after the system receives the start command, the control unit enters the preparation mode, activates the sensor module, and initializes the standard delivery pressure value (abbreviated as P), standard delivery flow value (abbreviated as Q), abnormal delivery pressure change rate (abbreviated as dP / dt, unit kPa / s), abnormal delivery flow change rate (abbreviated as dQ / dt, unit Nm 3 / s 2 ), transportation time dimension variable (abbreviated as Δt, unit s), historical trend parameter (abbreviated as H_trend), after the system parameters are initialized, the system enters the standby state and responds to material transportation needs at any time.

[0025] The system parameters are initialized by manual input for the first time, and are subsequently dynamically and automatically updated by the system according to the optimization rules. The optimization rules are explained in the subsequent steps.

[0026] In this application, the historical trend parameter is a normalized trend indicator used to reflect the comprehensive fluctuation of the current transportation status within a certain time window, mainly reflecting the trend change degree of system pressure and flow. The content of the historical trend parameter is empty when initialized, and the system will subsequently update the historical trend parameter.

[0027] The historical trend parameters are calculated by integrating multiple key factors to quantify the risk of blockage during the transportation process. These factors include: Pressure impact: Calculate the deviation between the current transportation pressure and the standard transportation pressure. When the pressure is close to the standard value, the risk is low; when the pressure is close to the maximum allowable pressure, the risk increases; Flow impact: Calculate the deviation between the current transportation flow and the standard transportation flow. When the flow is close to the standard value, the risk is low; when the flow is close to the minimum allowable flow, the risk increases; Pressure change rate impact: Calculate the rate of change of pressure over time, and compare it with the rate of change under abnormal transportation conditions. If the pressure changes too quickly, it means that there are fluctuations or mutations in the transportation system, and the risk of blockage increases; Flow change rate impact: Calculate the rate of change of flow over time, and compare it with the rate of change under abnormal transportation conditions. If the flow changes too quickly, it means that the transportation system is unstable and the risk of blockage increases; Abnormal transportation time impact: Calculate whether the current transportation time exceeds the preset range of normal transportation. If the transportation time is abnormal, it means that the system may be in an unstable state for a long time, and the risk of blockage increases.

[0028] S200, after the system enters the delivery state, the control unit calculates the valve opening corresponding to the standard delivery flow according to the initialized system parameters. At the same time, the system starts to collect pressure data and flow data in real time and stores them in the memory for subsequent trend analysis and adjustment.

[0029] In some embodiments, during the system transportation process, the sensor module collects pressure data and flow data in the pipeline at a fixed frequency of 1-5 seconds, preferably at a fixed frequency of 1 second. The fixed frequency of collection is obtained based on engineering experience and is the most preferred value after testing. Through high-frequency collection, early warning can be achieved, misjudgment can be reduced, and the system's response capability to transportation abnormalities can be improved.

[0030] S300, after the conveying process is completed, the system extracts features from the collected data and stores them in historical trend parameters.

[0031] In some embodiments, the historical trend parameters are suitable for recording the first feature, the second feature and the third feature: the first feature is the maximum pressure and the minimum flow during the delivery process, the second feature is filtering the pressure data and flow data using a fixed sliding time window, and calculating the maximum pressure change rate in the rising stage of delivery and the maximum flow change rate in the falling stage, and the third feature is to count the longest time period in which the pressure exceeds the standard delivery pressure value and continues to rise during the delivery process, and record whether blockage occurs.

[0032] In some embodiments, the sliding time window ranges from 10 to 60 seconds, preferably 15 seconds. The sliding time window is a filtering parameter selected based on engineering experience. Under this sliding time window, the fluctuations and abnormal changes of P and Q data can be more clearly reflected. In contrast, a time window that is too short can easily amplify instantaneous fluctuations and lead to misjudgment; while a window that is too long may mask mutation characteristics and reduce the sensitivity of anomaly detection.

[0033] In the third feature of the historical trend parameter suitable for recording, a delivery pressure value for determining whether a pipe is blocked is set for the system. When the delivery pressure exceeds this value, it can be considered that the pipe is blocked.

[0034] S400: Create multi-parameter combination rules to divide the transportation status into normal status, warning status, and critical congestion status. Select key operating variables that affect congestion during the transportation process from system parameters, process the key operating variables to form a congestion risk scoring model, derive a risk score based on the congestion risk scoring model, determine the current transportation status of the system, and then enable the system to implement corresponding measures.

[0035] The multi-parameter combination rules for normal conditions include: first, the maximum delivery pressure is equal to or lower than 90% of the standard delivery pressure; second, the minimum delivery flow is equal to or higher than 120% of the standard delivery flow; and third, the delivery time dimension variable is within the normal range. If the above conditions are met, the system is judged to be in a normal state. At this time, the risk score is in the low-risk range and the probability of congestion is low, indicating that the delivery process is stable and the equipment is operating within the optimization range.

[0036] The parameter combination rules for the early warning state include: the first condition, the maximum delivery pressure is between 90% and 120% of the standard delivery pressure, the second condition, the minimum delivery flow is between 100% and 120% of the standard delivery flow, the third condition, the pressure change rate or flow change rate exceeds 90% of the abnormal delivery change rate, and the third condition, the delivery time dimension variable is abnormal. If any of the above conditions is met, the system will be judged as a warning state. At this time, the risk score is in the medium risk range, and there is a certain probability of blockage, indicating that the delivery process is approaching a critical state. The system needs to closely monitor parameter changes to reduce the risk of blockage.

[0037] The parameter combination rules for the critical state of congestion include: the first condition, the maximum delivery pressure reaches or exceeds 120% of the standard delivery pressure; the second condition, the minimum delivery flow rate drops below 100% of the standard delivery flow rate; the third condition, the pressure change rate or flow change rate exceeds 90% of the abnormal delivery change rate; the third condition, the delivery time dimension variable continues to be abnormal. If any of the above conditions is met, the system will determine it as a critical state of congestion. At this time, the risk score is in the high-risk range, and the probability of congestion is high. The system should immediately take adjustment measures to avoid actual congestion.

[0038] It is worth noting that the low-risk range (e.g., <40%), medium-risk range (40%-80%), and high-risk range (e.g., >80%) of the risk score are set based on engineering experience and can be appropriately adjusted according to the specific system, for example, adjusting the upper limit of the low-risk range to 35%-45%.

[0039] In some embodiments, since the conveying time reflects the output capacity of the system, although the system output is constant and the volume of each feed is fixed, the actual filling rate of the material fluctuates, and the actual amount of material conveyed each time is not exactly the same, so the conveying time will vary. Under normal circumstances, the system calculates the actual filling rate of 60%-80% of the feed volume divided by the output of the system, which is suitable for obtaining the normal range of the conveying time. The conveying time outside this range is considered abnormal, which may indicate problems such as pipe blockage, air blowing or abnormal material status. If the conveying time dimension variable is outside the normal range, it is determined to be abnormal conveying behavior. If it exceeds 1.2 times the normal range of the conveying time dimension variable, it is determined to be a continuous abnormality.

[0040] For example: Assuming the feed volume is 1.0m³ each time, the system output is 0.1m³ / min, the normal range of feed rate is 1.0×60%~1.0×80%, 0.6~0.8m³, and normal conveying time = feed rate / output = 0.6 / 0.1~0.8 / 0.1 = 6~8 minutes. Therefore, a conveying time of 6-8 minutes is normal, and a time less than 6 minutes or greater than 8 minutes can be considered abnormal conveying behavior.

[0041] In some embodiments, key operating variables include pressure, flow, pressure change rate, flow change rate and abnormal duration. The key operating variables are converted into key factors to obtain the degree of deviation between the current pressure and the standard pressure, the degree of deviation between the current flow and the standard flow, whether the change rate of pressure and flow exceeds the abnormal state threshold, and whether the delivery time exceeds the normal range, and the key factors are normalized.

[0042] Specifically, if during a certain transportation, the pressure is close to the maximum allowable value (accounting for 90%), the flow rate drops to near the minimum allowable value (accounting for 95%), the pressure change rate is abnormal (accounting for 92%), the flow rate fluctuates violently (accounting for 88%), and the transportation time is obviously abnormal (accounting for 130%), then the comprehensive score may reach 0.89, corresponding to a congestion probability of approximately 89%.

[0043] Among them, the proportion of each value refers to the position of the current numerical value of a key operating variable within its set allowable range, that is, it is calculated through the relative relationship between the current value and the upper and lower limits. Specifically, the proportion can be obtained through the following formula: Proportion = (current value − minimum allowable value) / (maximum allowable value − minimum allowable value). The proportion result reflects the relative level of the variable within its effective operating range, which facilitates unified normalization processing and subsequent risk score analysis.

[0044] In some embodiments, the key factors are normalized to the [0, 1] range, and the system assigns different weights to each key factor according to its sensitivity to the congestion trend, constructs a weighted scoring model, and makes the resulting risk score fall within the [0, 1] range.

[0045] Since the units and dimensions of the variables are different, they must first be normalized. The normalization process is to standardize the current value of each variable according to its historical or set minimum and maximum values, and uniformly convert it into a dimensionless value between 0 and 1. For example, the normalized form of pressure is: (p_current-p_min) / (p_max-p_min). Other variables such as rate of change and duration can be processed in a similar manner to ensure that their values ​​fall within the interval [0,1].

[0046] Set the two values ​​in [0,1] as x and y. When the risk score is [0,x), it is judged as low risk, when the risk score is [x,y], it is judged as medium risk, and when the risk score is (y,1], it is judged as high risk. It can be used to provide early warning and locate high-risk transportation cycles.

[0047] The risk score calculation formula is: Risk score = w1×P_norm+w2×Q_norm+w3×dP / dt_norm+w4×dQ / dt_norm+w5×Δt_norm, where w1, w2, w3, w4, and w5 are weight values, P is pressure, Q is flow, dP / dt is the pressure change rate, dQ / dt is the flow change rate, and Δt is the abnormality duration.

[0048] The number of delivery times preset before the system is set as the initial delivery time. It is worth noting that in the initial delivery time, due to the small amount of data in the historical trend parameters, the system cannot make accurate data warnings. Therefore, it only makes predictions based on the strategy and does not perform pipe blockage warnings. The prediction results are still stored in the historical trend parameters for subsequent learning and adjustment. At this stage, the delivery status is determined based on the "standard delivery pressure value, standard delivery flow value, abnormal delivery pressure change rate, abnormal delivery flow change rate, abnormal delivery time dimension variable" input in step S100, combined with the logic of step S400. When the cumulative number of deliveries reaches a certain number (preferably 50 times, which can be adjusted according to actual conditions), the data of the historical trend parameters is updated and included in the pipe blockage warning mechanism.

[0049] In some embodiments, the preset number of times for the initial delivery is set to 50 times. When the number of deliveries reaches 50 times and the pipe blockage rate is less than 10%, the system corrects the prediction results of the historical trend parameters for the critical state of blockage and optimizes the initialized system parameters.

[0050] In this embodiment, it is shown that the current warning model parameters basically meet the actual transportation conditions, and there is no need to adjust key operating variables such as "standard transportation pressure value, standard transportation flow value, abnormal transportation pressure change rate, abnormal transportation flow change rate, abnormal transportation time dimension variable". At this time, the judgment conditions of the critical state of blockage can be appropriately relaxed to improve the system's tolerance for marginal conditions and reduce the false alarm rate. The specific relaxation strategy examples are as follows: the first condition of "the maximum transportation pressure reaches or exceeds 120% of the standard transportation pressure" can be adjusted to 120%-130%; the second condition of "the minimum transportation flow drops below 100% of the standard transportation flow" can be adjusted to 90%-100%; the third condition of "the pressure change rate or flow change rate exceeds 90% of the abnormal change rate" can be adjusted to 90%-95%; the fourth condition of "the transportation time dimension variable continues to be abnormal and exceeds 1.2 times the normal range" can be adjusted to 120%-150%. The above optimization adjustments can enhance the practicality and flexibility of the model while ensuring system stability. In some embodiments, when the number of deliveries reaches 50 times and the pipe blocking rate is not less than 10%, the system further compares the predicted results of the historical trend parameters with the actual pipe blocking situation and adjusts the initialized system parameters.

[0051] In this embodiment, it indicates that the current warning model parameters no longer conform to the actual transportation conditions and there is a risk of misjudgment or missed judgment. At this time, it is necessary to re-evaluate and appropriately adjust key operating variables such as "standard transportation pressure value, standard transportation flow value, abnormal transportation pressure change rate, abnormal transportation flow change rate, abnormal transportation time dimension variable". At the same time, in order to improve the sensitivity of the model, the various blockage judgment conditions should be appropriately tightened and the judgment threshold range should be narrowed, that is, the values ​​of the relevant judgment parameters should be lowered, so as to more accurately identify potential pipe blockage risks and improve the response timeliness and accuracy of the early warning system.

[0052] S500: When the number of conveying times reaches the preset number, the system optimizes the initialized system parameters and the judgment conditions of each conveying state according to the pipe blockage rate. During the subsequent conveying process, the system performs a pipe blockage warning based on the new system parameters and the judgment conditions of the conveying state, thereby improving the stability and reliability of the conveying process.

[0053] The present application also provides a pneumatic conveying system, which applies the anti-blocking and optimized pneumatic conveying intelligent control method of any of the above embodiments.

[0054] By introducing the pressure change rate (dP / dt), flow change rate (dQ / dt) and abnormal duration (Δt), this application can monitor the pressure and flow change trends and abnormal duration, identify the risk of blockage in advance, and achieve early identification of the risk of blockage, avoiding the hysteresis of the traditional method that only alarms after the parameters reach the limit value. Then, by combining pressure (P), flow (Q), pressure change rate (dP / dt), flow change rate (dQ / dt) and historical trend parameters (H_trend), a multi-dimensional judgment rule is constructed to improve the judgment accuracy and robustness, reduce false alarms and missed alarms, and according to the differences in the influence of different materials and conveying conditions, the historical trend analysis parameters (H_trend) and dynamic time windows (such as 10-60 seconds) are used to achieve adaptive optimization parameters to adapt to diverse scenarios.

[0055] This application is based on intelligent control logic, and calculates and outputs optimization signals in real time (such as adjusting air flow speed and suspending feeding), quickly responds to blockage risks, improves anti-blocking efficiency, and prevents blockages from occurring. In addition, by introducing historical trend analysis parameters (H_trend) to analyze historical data, historical data is used to predict risks and potential blockage points, and operating parameters are optimized in advance to ensure the long-term stable operation of the system and improve transportation efficiency.

[0056] The above describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above embodiments. The above embodiments and the specification only describe the principles of the present application. Various changes and improvements may be made to the present application without departing from the spirit and scope of the present application. These changes and improvements fall within the scope of the present application to be protected, and the scope of protection claimed by the present application is defined by the attached claims and their equivalents.

Claims

1. An intelligent control method for anti-blocking and optimized pneumatic conveying, characterized in that: Including steps: S100: The system receives a start command, the control unit enters a preparation mode, activates the sensor module, and initializes system parameters including the standard delivery pressure value, the standard delivery flow value, the abnormal delivery pressure change rate, the abnormal delivery flow change rate, the delivery time dimension variable, and the historical trend parameter. After the initialization is completed, the system enters a standby state; S200, the system enters the delivery state, the control unit calculates the valve opening corresponding to the standard delivery flow according to the initialized system parameters, and the system starts to collect pressure data and flow data in real time and store them in the memory; S300, after the conveying process is completed, the system extracts features from the collected data and stores them in historical trend parameters; S400: Create a multi-parameter combination rule to classify the transport state into a normal state, a warning state, and a critical congestion state. Select key operating variables that affect congestion during the transport process from the system parameters. Process these key operating variables to form a congestion risk scoring model. Determine the risk score based on the congestion risk scoring model, determine the current transport state of the system, and then cause the system to take appropriate measures. S500: When the number of transports reaches the preset number, the system optimizes the initialized system parameters and the judgment conditions of each transport state according to the pipe blockage rate. During the subsequent transport process, the system performs a pipe blockage warning based on the new system parameters and the judgment conditions of the transport state.

2. The anti-blocking and optimized pneumatic conveying intelligent control method according to claim 1, characterized in that: Key operating variables include pressure, flow, pressure change rate, flow change rate and abnormal duration. The key operating variables are converted into key factors to obtain the degree of deviation between the current pressure and the standard pressure, the degree of deviation between the current flow and the standard flow, whether the pressure and flow change rates exceed the abnormal state threshold, and whether the delivery time exceeds the normal range, and the key factors are normalized.

3. The anti-blocking and optimized pneumatic conveying intelligent control method according to claim 2, characterized in that: Normalize key factors to the range of [0,1]. The system assigns different weights to each key factor based on its sensitivity to congestion trends, constructs a weighted scoring model, and ensures that the resulting risk score is within the range of [0,1]. Assume that the two values ​​in [0,1] are x and y. When the risk score is [0,x), it is judged as low risk, when the risk score is [x,y], it is judged as medium risk, and when the risk score is (y,1], it is judged as high risk. The risk score calculation formula is: risk score = w1×P_norm+w2×Q_norm+w3×dP / dt_norm+w4×dQ / dt_norm+w5×Δt_norm, where w1, w2, w3, w4, and w5 are weight values, P is pressure, Q is flow, dP / dt is the pressure change rate, dQ / dt is the flow change rate, and Δt is the abnormality duration. The initialized system parameters are manually input for the first time and are subsequently dynamically updated by the system according to the optimization rules.

4. The anti-blocking and optimized pneumatic conveying intelligent control method according to claim 1, characterized in that: The multi-parameter combination rules for the normal state include: the first condition, the maximum delivery pressure is equal to or lower than 90% of the standard delivery pressure; the second condition, the minimum delivery flow is equal to or higher than 120% of the standard delivery flow; the third condition, the delivery time dimension variable is within the normal range. If the above conditions are met, the system is judged to be in a normal state; The parameter combination rules for the warning state include: the first condition, the maximum delivery pressure is between 90% and 120% of the standard delivery pressure; the second condition, the minimum delivery flow rate is between 100% and 120% of the standard delivery flow rate; the third condition, the pressure change rate or flow change rate exceeds 90% of the abnormal delivery change rate; the third condition, the delivery time dimension variable is abnormal. If any of the above conditions are met, the system will be judged as a warning state; The parameter combination rules for the critical blockage state include: the first condition, the maximum delivery pressure reaches or exceeds 120% of the standard delivery pressure; the second condition, the minimum delivery flow rate drops below 100% of the standard delivery flow rate; the third condition, the pressure change rate or flow change rate exceeds 90% of the abnormal delivery change rate; the third condition, the delivery time dimension variable continues to be abnormal. If any of the above conditions is met, the system will determine it as a critical blockage state.

5. The anti-blocking and optimized pneumatic conveying intelligent control method according to claim 4, characterized in that: The system calculates the actual filling rate of 60%-80% of the feed volume divided by the system output, which is suitable for obtaining the normal range of conveying time. If the conveying time dimension variable is outside the normal range, it is judged as abnormal conveying behavior. If it exceeds 1.2 times the normal range of the conveying time dimension variable, it is judged as a continuous abnormality.

6. The anti-blocking and optimized pneumatic conveying intelligent control method according to claim 4, characterized in that: The historical trend parameters are suitable for recording the first, second, and third features: the first feature is the maximum pressure and minimum flow rate during the transportation process; the second feature is filtering the pressure data and flow rate data using a fixed sliding time window, and calculating the maximum pressure change rate in the rising stage of transportation and the maximum flow rate change rate in the falling stage; the third feature is to count the longest time period in which the pressure exceeds the standard transportation pressure value and continues to rise during the transportation process, and record whether pipe blockage occurs; the sliding time window range is 10-60 seconds.

7. The anti-blocking and optimized pneumatic conveying intelligent control method according to claim 1, characterized in that: When the number of delivery times reaches 50 and the pipe blockage rate is less than 10%, the system corrects the prediction results of the historical trend parameters for the critical state of blockage and optimizes the initialized system parameters; when the number of delivery times reaches 50 and the pipe blockage rate is not less than 10%, the system further compares the prediction results of the historical trend parameters with the actual pipe blockage situation and adjusts the initialized system parameters.

8. The anti-blocking and optimized pneumatic conveying intelligent control method according to claim 1, characterized in that: The number of delivery times preset by the system is set as the initial delivery stage. In the initial delivery stage, the system only makes predictions based on strategies and does not perform pipe blockage warnings. The prediction results are stored in the historical trend parameters.

9. The anti-blocking and optimized pneumatic conveying intelligent control method according to claim 1, characterized in that: The content of historical trend parameters is empty when initialized; during the system transportation process, the sensor module collects pressure data and flow data in the pipeline at a fixed frequency of 1-5 seconds.

10. A pneumatic conveying system, characterized in that: The anti-blocking and optimized pneumatic conveying intelligent control method according to any one of claims 1 to 9 is applied.