Dedusting oscillation control method and system for ash conveying pipeline

Abstract

The invention discloses a dedusting oscillation control method and system for an ash conveying pipeline, and aims to solve the problem that the ash blocking state of the pipeline cannot be accurately predicted and dedusting oscillation parameters cannot be adaptively optimized in the prior art. The method comprises the following steps: collecting pipeline state data of an ash conveying pipeline through a multi-mode sensor, and obtaining physical characteristics of the pipeline; wherein the pipeline physical characteristics comprise a plurality of dimension state characteristics; determining a basic risk coefficient of the ash conveying pipeline according to the physical characteristics of the pipeline and the ash matter type of the ash matter in the ash conveying pipeline; then correcting the basic risk coefficient according to a rule matching result of the physical characteristics of the pipeline in the constructed association rule base to obtain an ash clogging risk coefficient; therefore, when the ash blocking risk coefficient meets the set optimization condition, oscillation strategy optimization is automatically carried out on the ash conveying pipeline.

Description

Technical Field

[0001] This application relates to the field of ash conveying pipeline technology, and in particular to a dust removal vibration control method and system for ash conveying pipelines. Background Technology

[0002] In pneumatic ash conveying systems in the industrial sector, dust collection pipelines play a crucial role in transporting fly ash. However, during actual operation, factors such as decreasing ash temperature, changes in humidity, and ash properties can easily lead to "ash buildup" inside the pipelines. This reduces the flow cross-section, increases conveying resistance, and ultimately causes pipeline blockage. Pipeline blockage not only affects production continuity but also causes unplanned downtime, resulting in significant economic losses.

[0003] Currently, the main technical solutions for preventing and clearing blockages in ash conveying pipelines are as follows: Fixed-parameter oscillation technology: This method uses acoustic or mechanical oscillators with preset frequencies and intensities, operating at fixed time intervals. This method lacks specificity, cannot be adjusted according to the actual condition of the pipeline, and suffers from energy waste and severe equipment wear.

[0004] A simple control technique based on a single sensor: This technique monitors the pipeline status using a single sensor such as temperature or pressure, and triggers a clearing action when an anomaly is detected. While this method is an improvement over fixed-parameter techniques, it suffers from high false alarm and false negative rates due to its reliance on a single data source, and it cannot achieve early prediction.

[0005] Preventative oscillation technology based on timed intervals: This method involves setting a fixed working cycle for preventative oscillation based on experience. While it can prevent dust blockage to some extent, it lacks scientific basis, may consume energy unnecessarily, and fail to respond promptly when truly needed.

[0006] Human experience-based judgment technology: This method relies on the operator's experience to determine the status and adjust parameters. It is highly subjective, greatly affected by the operator's skill level, and cannot achieve accurate 24 / 7 monitoring. Summary of the Invention

[0007] This application provides a dust removal vibration control method for ash conveying pipelines, which solves the problem in the prior art that it is impossible to accurately predict the ash blockage state of the pipeline and adaptively optimize the dust removal vibration parameters.

[0008] This application also provides a dust removal vibration control system for ash conveying pipelines.

[0009] The embodiments of this application adopt the following technical solutions: In a first aspect, this application provides a dust collection vibration control method for ash conveying pipelines, comprising: The pipeline status data of the ash conveying pipeline is collected by multimodal sensors to obtain the pipeline physical characteristics; the pipeline physical characteristics include multiple dimensions of status characteristics; The basic risk coefficient of the ash conveying pipeline is determined based on the physical characteristics of the pipeline and the type of ash in the ash conveying pipeline. Based on the rule matching results of the pipeline's physical characteristics in the constructed association rule base, the basic risk coefficient is corrected to obtain the ash blockage risk coefficient. When the ash blockage risk coefficient meets the set optimization conditions, the ash conveying pipeline is optimized using an oscillation strategy.

[0010] Optionally, the physical characteristics of the pipeline include: temperature state characteristics, acoustic state characteristics, vibration state characteristics, humidity state characteristics, and ash accumulation thickness characteristics; the pipeline physical characteristics are obtained by collecting pipeline state data of the ash conveying pipeline through multi-modal sensors. The temperature state characteristics are determined based on the axial temperature gradient and circumferential temperature standard deviation of the pipeline in the pipeline condition data. Based on the bandwidth energy value, acoustic dominant frequency and spectral kurtosis in the pipeline condition data, as well as the first reference value, second reference value and third reference value corresponding to the bandwidth energy value, acoustic dominant frequency and spectral kurtosis respectively, the acoustic condition characteristics are determined; Based on the vibration amplitude and actual damping ratio of the pipeline at its natural frequency in the pipeline condition data, and compared with the reference amplitude and reference damping ratio of the clean pipeline, the vibration state characteristics are determined. The humidity state characteristics are determined based on the volumetric water content and critical water content threshold in the pipeline condition data. The characteristics of ash accumulation thickness are determined based on the thermal response time constants of the pipeline condition data, the thermal response time constants of the clean pipeline, and the thermal response time constants of the completely blocked pipeline.

[0011] Optionally, the basic risk coefficient of the ash conveying pipeline shall be determined based on the pipeline's physical characteristics and the type of ash in the pipeline, including: Based on the temperature, acoustic, vibration, humidity, and ash thickness characteristics, the ash type is used as the risk tolerance coefficient to determine the basic risk coefficient of the ash conveying pipeline.

[0012] Optionally, the basic risk coefficient is modified based on the rule matching results of the constructed association rule base according to the physical characteristics of the pipeline to obtain the ash blockage risk coefficient, including: Based on the feature values ​​of temperature state characteristics, acoustic state characteristics, vibration state characteristics, humidity state characteristics, and dust accumulation thickness characteristics, the system matches them with the rule conditions in the association rule base. Calculate the risk adjustment value for each successfully matched rule; whereby the risk adjustment value for each rule is determined based on the confidence, support, and lift of each rule. The risk correction values ​​of each rule are merged to obtain the related rule correction items; The association rule correction term and the basic risk coefficient are nonlinearly fused to obtain the ash-blocking risk coefficient; the nonlinear fusion uses the following formula:

[0013] in, To account for the risk factor of dust blockage, Basic risk coefficient, For association rule correction items, These are the weighting coefficients. This is the Sigmoid activation function.

[0014] Optionally, historical operating data can be collected, including the physical characteristics of the pipeline under normal conditions and various ash blockage conditions. Discretize the physical characteristics of the pipeline to transform them from continuous to discrete features; Frequent pattern mining algorithms are used to extract frequent feature combinations from discrete features; Multiple association rules are generated based on the frequent feature combinations obtained from mining. Each association rule is in the form of: IF{feature condition combination} THEN{risk correction value}, and the confidence, support and lift of each rule are calculated. Multiple association rules are filtered based on confidence, support, and lift to obtain an association rule library.

[0015] Optionally, the oscillation strategy for the ash conveying pipeline can be optimized, including: The risk level is determined based on the ash blockage risk coefficient, and the risk levels include four levels: low risk, medium risk, high risk and extremely high risk. Select the corresponding basic oscillation mode based on the risk level; the basic oscillation modes include prevention mode, clearing mode and reinforcement mode; Based on the basic oscillation mode, the oscillation parameters are adjusted according to the physical characteristics of the pipeline; the oscillation parameters include oscillation frequency, oscillation intensity and oscillation duration.

[0016] Secondly, this application provides a dust collection vibration control system for ash conveying pipelines, the system comprising: The acquisition unit is used to collect pipeline status data of the ash conveying pipeline through a multimodal sensor to obtain the pipeline physical characteristics; wherein, the pipeline physical characteristics include multiple dimensions of status characteristics; The determination unit is used to determine the basic risk coefficient of the ash conveying pipeline based on the pipeline's physical characteristics and the type of ash in the ash conveying pipeline; The matching correction unit is used to correct the basic risk coefficient based on the rule matching results in the constructed association rule base according to the physical characteristics of the pipeline, so as to obtain the ash blockage risk coefficient. The optimization unit is used to optimize the oscillation strategy of the ash conveying pipeline when the ash blockage risk coefficient meets the set optimization conditions.

[0017] Optionally, this acquisition unit is specifically used for: The temperature state characteristics are determined based on the axial temperature gradient and circumferential temperature standard deviation of the pipeline in the pipeline condition data. Based on the bandwidth energy value, acoustic dominant frequency and spectral kurtosis in the pipeline condition data, as well as the first reference value, second reference value and third reference value corresponding to the bandwidth energy value, acoustic dominant frequency and spectral kurtosis respectively, the acoustic condition characteristics are determined; Based on the vibration amplitude and actual damping ratio of the pipeline at its natural frequency in the pipeline condition data, and compared with the reference amplitude and reference damping ratio of the clean pipeline, the vibration state characteristics are determined. The humidity state characteristics are determined based on the volumetric water content and critical water content threshold in the pipeline condition data. The characteristics of ash accumulation thickness are determined based on the thermal response time constants of the pipeline condition data, the thermal response time constants of the clean pipeline, and the thermal response time constants of the completely blocked pipeline.

[0018] Optionally, this determining unit is specifically used for: Based on temperature, acoustic, vibration, humidity, and ash thickness characteristics, the basic risk coefficient of the ash conveying pipeline is determined using ash type as the risk tolerance coefficient.

[0019] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: The method provided in this application allows for the acquisition of pipeline state data from ash conveying pipelines using multimodal sensors to obtain pipeline physical characteristics. These physical characteristics include multiple dimensions of state features. Based on these physical characteristics and the type of ash in the pipeline, a basic risk coefficient is determined. The basic risk coefficient is then corrected based on the rule matching results of the pipeline physical characteristics in a constructed association rule base, resulting in a blockage risk coefficient. When the blockage risk coefficient meets the set optimization conditions, an oscillation strategy is optimized for the ash conveying pipeline. This method acquires multiple dimensions of state features from the ash conveying pipeline, adaptively calculates the basic risk coefficient based on the ash type, and then introduces it into an association rule base for real-time pattern matching and risk correction. This enables accurate prediction of blockage risk and adaptive dynamic optimization of dust removal oscillation parameters. It significantly improves pipeline operational reliability, substantially reduces the risk of unplanned downtime and blockage clearing energy consumption, and forms a closed-loop intelligent maintenance system from state perception and intelligent diagnosis to precise control. Attached Figure Description

[0020] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A schematic diagram illustrating the implementation process of a dust removal vibration control method for ash conveying pipelines provided in this application embodiment; Figure 2 This application provides a schematic diagram of the specific structure of a dust removal vibration control system for an ash conveying pipeline. Detailed Implementation To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] As will be known to those skilled in the art, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0022] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application.

[0023] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0024] Example 1 To address the problem of existing technologies being unable to accurately predict pipeline blockage and adaptively optimize dust removal vibration parameters, this application provides a dust removal vibration control method for ash conveying pipelines.

[0025] Specifically, the implementation flow of the method provided in this application embodiment is as follows: Figure 1 As shown, it includes the following steps: Step 11: Collect pipeline status data of the ash conveying pipeline through multimodal sensors to obtain pipeline physical characteristics; wherein, pipeline physical characteristics include multiple dimensions of status characteristics.

[0026] In this embodiment of the application, the physical characteristics of the pipeline include: temperature state characteristics, acoustic state characteristics, vibration state characteristics, humidity state characteristics, and dust accumulation thickness characteristics.

[0027] Specifically, a mobile multimodal sensor inspection platform can be deployed in key sections of the ash conveying pipeline, such as elbows, diameter changes, and the ends of horizontal sections—areas prone to blockage. This platform can consist of a walking mechanism, protective cover, power supply unit, and data acquisition system, and can move along a track laid on the outer wall of the pipeline at a speed of 0.3-0.8 m / s. The multimodal sensors can include an infrared thermal imager, an acoustic sensor, a vibration sensor, and a microwave humidity sensor. The infrared thermal imager can be an uncooled infrared focal plane array with a resolution of 640×480 pixels, a temperature measurement range of 0-200℃, and an accuracy of ±1℃. Temperature field data is collected every 0.5 meters along the pipeline axis, with temperature values ​​collected at 12 equally divided points circumferentially for each cross-section, at a sampling frequency of 1Hz. The acoustic sensor can be a broadband acoustic sensor with a frequency response range of 5kHz-25kHz and a dynamic range ≥100dB. Spectral analysis is performed using a 1024-point FFT, with a sampling frequency of 50kHz, and sound pressure signals are continuously acquired. The vibration sensor can be a triaxial ICP-type accelerometer with a range of ±50g and a frequency range of 0.5-5kHz. It focuses on monitoring the vibration response of the pipeline near its natural frequency (typically 20-80Hz), with a sampling frequency of 2kHz. The microwave humidity sensor can be a 5.8GHz band microwave sensor with a measurement depth of 0-30mm, a volumetric water content measurement range of 0-15%, an accuracy of ±0.5%, and direct contact measurement, acquiring data every 10 seconds.

[0028] Pipeline condition data includes temperature distribution data: axial gradient value and circumferential standard deviation; acoustic spectrum data: 10-20kHz band energy, dominant frequency and spectral kurtosis; vibration response data: vibration amplitude at natural frequency and actual damping ratio; humidity measurement data: volumetric water content; and thermal inertia data: thermal response time constant.

[0029] In one embodiment, the acquisition of pipeline status data of the ash conveying pipeline by using a multimodal sensor to obtain the pipeline's physical characteristics includes: The temperature state characteristics are determined based on the axial temperature gradient and circumferential temperature standard deviation of the pipeline in the pipeline condition data. Based on the bandwidth energy value, acoustic dominant frequency and spectral kurtosis in the pipeline condition data, as well as the first reference value, second reference value and third reference value corresponding to the bandwidth energy value, acoustic dominant frequency and spectral kurtosis respectively, the acoustic condition characteristics are determined; Based on the vibration amplitude and actual damping ratio of the pipeline at its natural frequency in the pipeline condition data, and compared with the reference amplitude and reference damping ratio of the clean pipeline, the vibration state characteristics are determined. The humidity state characteristics are determined based on the volumetric water content and critical water content threshold in the pipeline condition data. The characteristics of ash accumulation thickness are determined based on the thermal response time constants of the pipeline condition data, the thermal response time constants of the clean pipeline, and the thermal response time constants of the completely blocked pipeline.

[0030] Specifically, the formula for calculating the temperature state characteristics is as follows: (Formula 1) in, This represents the axial temperature gradient value of the pipeline. This represents the standard deviation of the circumferential temperature of the pipeline.

[0031] The formula for calculating acoustic state characteristics is as follows: (Formula 2) (Formula 3) in, These are unnormalized acoustic state characteristics. The acoustic state characteristics are normalized. Energy in the 10-20kHz frequency band (dB). The acoustic dominant frequency, For spectral kurtosis, As the first benchmark value, This is the second benchmark value. The third reference value is the first, second, and third reference values, which are the frequency band energy reference value, the dominant frequency reference value, and the spectral kurtosis reference value under normal flow conditions, respectively. , and These are the weighting coefficients. + + =1.

[0032] The formula for calculating vibration state characteristics is as follows: (Formula 4) in, The vibration amplitude at the natural frequency. This is the actual damping ratio. The reference amplitude for clean pipelines, The reference damping ratio for clean pipelines, and These are the weighting coefficients. .

[0033] The formula for calculating humidity state characteristics is as follows: (Formula 5) in, Water content by volume This is the critical water content threshold.

[0034] The formula for calculating the characteristic of dust accumulation thickness is as follows: (Formula 6) in, The thermal response time constant, The thermal response time constant of the clean pipeline. The thermal response time constant for complete blockage.

[0035] Step 12: Determine the basic risk coefficient of the ash conveying pipeline based on the pipeline's physical characteristics and the type of ash in the ash conveying pipeline.

[0036] In this embodiment of the application, the determination of the basic risk coefficient of the ash conveying pipeline based on the physical characteristics of the pipeline and the type of ash in the ash conveying pipeline includes: determining the basic risk coefficient of the ash conveying pipeline based on temperature state characteristics, acoustic state characteristics, vibration state characteristics, humidity state characteristics and ash accumulation thickness characteristics, using the ash type as a risk tolerance coefficient.

[0037] Specifically, the type of ash in the current ash conveying pipeline is queried from a pre-established ash quality characteristic database and mapped to a risk tolerance coefficient. Then, the weighted geometric mean model is used to calculate the basic risk coefficient. The specific calculation formula is as follows: (Formula 7) in, , , , , The weights for temperature state characteristics, acoustic state characteristics, vibration state characteristics, humidity state characteristics, and dust accumulation thickness characteristics are determined based on expert experience. This is the risk tolerance coefficient.

[0038] In one specific implementation, the ash types include: low-calcium fly ash, medium-calcium fly ash, high-calcium fly ash, high-iron fly ash, and other special ash types. For example, the risk tolerance coefficient can be set to 0.85 for low-calcium fly ash, 1.00 for medium-calcium fly ash, 1.15 for high-calcium fly ash, 1.25 for high-iron fly ash, and the risk tolerance coefficient for other special ash types can be set to 0.8~1.4.

[0039] Step 13: Based on the rule matching results of the pipeline physical characteristics in the constructed association rule base, the basic risk coefficient is corrected to obtain the ash blockage risk coefficient.

[0040] In this embodiment, it specifically includes: Based on the feature values ​​of temperature state characteristics, acoustic state characteristics, vibration state characteristics, humidity state characteristics, and dust accumulation thickness characteristics, the system matches them with the rule conditions in the association rule base. Calculate the risk adjustment value for each successfully matched rule; whereby the risk adjustment value for each rule is determined based on the confidence, support, and lift of each rule. The risk correction values ​​of each rule are merged to obtain the related rule correction items; The association rule correction term and the basic risk coefficient are nonlinearly fused to obtain the ash-blocking risk coefficient; the nonlinear fusion uses the following formula: (Formula 8) in, To account for the risk factor of dust blockage, Basic risk coefficient, For association rule correction items, These are the weighting coefficients. This is the Sigmoid activation function.

[0041] In one specific implementation, constructing an association rule base includes: Collect historical operating data, which includes the physical characteristics of the pipeline under normal conditions and various ash blockage conditions; The physical characteristics of the pipeline are discretized to transform them from continuous features into discrete features; A frequent pattern mining algorithm is used to extract frequent feature combinations from the discrete features; Multiple association rules are generated based on the frequent feature combinations obtained from mining. Each association rule is in the form of: IF{feature condition combination} THEN{risk correction value}, and the confidence, support and lift of each rule are calculated. The association rule library is obtained by filtering the multiple association rules based on the confidence level, the support level, and the lift level.

[0042] Specifically, historical operational data is extracted from the database, including the physical characteristics of pipelines under normal and various ash-blocking conditions. The data collection period is 12 consecutive months, covering different seasons and load conditions. Next, the continuous feature values ​​are converted into discrete interval labels to facilitate association rule mining. The FP-Growth algorithm is used to mine frequent feature combinations from the discretized features. Minimum support and minimum confidence are set. For example, the minimum support is set to 0.05 and the minimum confidence to 0.7. Association rules are generated based on frequent feature combinations, with the rule format: IF{feature condition combination} THEN{risk correction value}. Example of rule generation: Rule 1:

[0043] Rule 2:

[0044] Rule 3:

[0045] Next, support, confidence, and lift are calculated for each rule. Support is the probability of a rule appearing in the dataset, confidence is the conditional probability of the rule being true, and lift is an indicator of the rule's effectiveness. Finally, rules are filtered based on support, confidence, and lift. Rules with support greater than 0.05 and confidence greater than or equal to 0.7 are retained, ultimately forming a relational rule base containing many high-quality rules.

[0046] Based on the established association rule base, in real-time, the feature values ​​of temperature, acoustic, vibration, humidity, and dust accumulation thickness are first matched with the rule conditions in the association rule base. After matching, multiple rules are obtained, and for each rule, its risk correction value is calculated. The specific calculation formula is as follows: (Formula 9) in, For each rule, a risk adjustment value is set. A preset base correction value for each rule. The confidence level of the rule. For the support of the rules, The degree of improvement of the rules.

[0047] The risk correction values ​​of all rules are combined to obtain a comprehensive correction term. The specific technical formula is as follows: (Formula 10) in, For rules The risk correction value, For rules The weights are determined based on rule quality calculations.

[0048] Finally, the basic risk coefficient and the key rule correction term are nonlinearly fused using Formula 8 to obtain the ash blockage risk coefficient.

[0049] In one example, assuming a baseline risk coefficient R_b = 0.65 for a certain measurement point, two rules are matched: Matching results for Rule 1: Rule conditions: , Base correction value: , Quality Indicators: , Rule 1 Risk Adjustment Value: .

[0050] Matching results for Rule 2: Rule conditions: , Base correction value: , Quality Indicators: , Rule 2 Risk Adjustment Value: .

[0051] Correction term calculation: Weighted sum: , Correction items: , Final risk coefficient calculation: Linear combination: , Sigmoid transform: .

[0052] Step 14: When the ash blockage risk coefficient meets the set optimization conditions, the ash conveying pipeline is optimized by oscillation strategy.

[0053] In one embodiment, the oscillation strategy optimization of the ash conveying pipeline includes: The risk level is determined based on the ash blockage risk coefficient, and the risk levels include four levels: low risk, medium risk, high risk and extremely high risk. Select the corresponding basic oscillation mode based on the risk level; the basic oscillation modes include prevention mode, clearing mode and reinforcement mode; Based on the basic oscillation mode, the oscillation parameters are adjusted according to the physical characteristics of the pipeline; the oscillation parameters include oscillation frequency, oscillation intensity and oscillation duration.

[0054] In this embodiment, the risk status is divided into four levels according to the ash blockage risk coefficient R, as shown in Table 1 below.

[0055] Table 1:

[0056] The basic oscillation pattern corresponding to each risk level: Precautionary mode (medium risk): Basic frequency: Basic strength: Base duration: = 30 s, Working mode: intermittent, working cycle 5 minutes. Clearance mode (high risk): Base frequency: Basic strength: Base duration: Working mode: Continuous operation, repeated 2-3 times if necessary. Enhanced mode (extremely high risk): Base frequency: Basic strength: Base duration: Working method: Continuous reinforcement until the risk factor is reduced.

[0057] Building upon the aforementioned basic oscillation pattern, and to improve control precision, a further refined adjustment of the oscillation parameters based on the pipeline's physical characteristics was designed.

[0058] Specifically, the oscillation frequency is determined by comprehensively considering the characteristics of ash accumulation, ash type, and risk level.

[0059]

[0060] (Formula 11) in, For thickness influence coefficient, Humidity influence coefficient This is the risk level impact coefficient. Frequency restriction conditions: .

[0061] The intensity of the oscillation is determined by the risk level and the severity of dust accumulation.

[0062]

[0063] (Formula 12) in, To minimize workload, For the maximum allowable strength, The intensity growth coefficient, The strength initiation threshold, This is the thickness enhancement factor.

[0064] The duration of oscillation is determined by the saturation effect of the blockage clearing effect.

[0065]

[0066] (Formula 13) in, For the shortest action time, The longest allowed time, This is a duration adjustment factor. This is the thickness duration coefficient.

[0067] The method provided in this application allows for the acquisition of pipeline state data from ash conveying pipelines using multimodal sensors to obtain pipeline physical characteristics. These physical characteristics include multiple dimensions of state features. Based on these physical characteristics and the type of ash in the pipeline, a basic risk coefficient is determined. The basic risk coefficient is then corrected based on the rule matching results of the pipeline physical characteristics in a constructed association rule base, resulting in a blockage risk coefficient. When the blockage risk coefficient meets the set optimization conditions, an oscillation strategy is optimized for the ash conveying pipeline. This method acquires multiple dimensions of state features from the ash conveying pipeline, adaptively calculates the basic risk coefficient based on the ash type, and then introduces it into an association rule base for real-time pattern matching and risk correction. This enables accurate prediction of blockage risk and adaptive dynamic optimization of dust removal oscillation parameters. It significantly improves pipeline operational reliability, substantially reduces the risk of unplanned downtime and blockage clearing energy consumption, and forms a closed-loop intelligent maintenance system from state perception and intelligent diagnosis to precise control.

[0068] Example 2 To address the limitations of existing technologies in accurately predicting pipeline blockage and adaptively optimizing dust collection vibration parameters, this application provides a dust collection vibration control system for ash conveying pipelines. A schematic diagram of the specific structure of this control system is shown below. Figure 2 As shown, it includes an acquisition unit 21, a determination unit 22, a matching correction unit 23, and an optimization unit 24. The functions of each unit are as follows: The acquisition unit 21 is used to collect pipeline status data of the ash conveying pipeline through a multimodal sensor to obtain the pipeline physical characteristics; wherein, the pipeline physical characteristics include multiple dimensions of status characteristics; Unit 22 is used to determine the basic risk coefficient of the ash conveying pipeline based on the pipeline's physical characteristics and the type of ash in the ash conveying pipeline. The matching correction unit 23 is used to correct the basic risk coefficient based on the rule matching results in the constructed association rule base according to the physical characteristics of the pipeline, so as to obtain the ash blockage risk coefficient. The optimization unit 24 is used to optimize the oscillation strategy of the ash conveying pipeline when the ash blockage risk coefficient meets the set optimization conditions.

[0069] Optionally, the acquisition unit 21 is specifically used for: The temperature state characteristics are determined based on the axial temperature gradient and circumferential temperature standard deviation of the pipeline in the pipeline condition data. Based on the bandwidth energy value, acoustic dominant frequency and spectral kurtosis in the pipeline condition data, as well as the first reference value, second reference value and third reference value corresponding to the bandwidth energy value, acoustic dominant frequency and spectral kurtosis respectively, the acoustic condition characteristics are determined; Based on the vibration amplitude and actual damping ratio of the pipeline at its natural frequency in the pipeline condition data, and compared with the reference amplitude and reference damping ratio of the clean pipeline, the vibration state characteristics are determined. The humidity state characteristics are determined based on the volumetric water content and critical water content threshold in the pipeline condition data. The characteristics of ash accumulation thickness are determined based on the thermal response time constants of the pipeline condition data, the thermal response time constants of the clean pipeline, and the thermal response time constants of the completely blocked pipeline.

[0070] Optionally, the determining unit 22 is specifically used for: Based on temperature, acoustic, vibration, humidity, and ash thickness characteristics, the basic risk coefficient of the ash conveying pipeline is determined using ash type as the risk tolerance coefficient.

[0071] Optionally, the matching correction unit 23 is specifically used for: Based on the feature values ​​of temperature state characteristics, acoustic state characteristics, vibration state characteristics, humidity state characteristics, and dust accumulation thickness characteristics, the system matches them with the rule conditions in the association rule base. Calculate the risk adjustment value for each successfully matched rule; whereby the risk adjustment value for each rule is determined based on the confidence, support, and lift of each rule. The risk correction values ​​of each rule are merged to obtain the related rule correction items; The association rule correction term and the basic risk coefficient are nonlinearly fused to obtain the ash-blocking risk coefficient; the nonlinear fusion uses the following formula:

[0072] in, To account for the risk factor of dust blockage, Basic risk coefficient, For association rule correction items, These are the weighting coefficients. This is the Sigmoid activation function. (Optional) Optionally, the system also includes building blocks, specifically for: Collect historical operating data, which includes the physical characteristics of the pipeline under normal conditions and various ash blockage conditions; Discretize the physical characteristics of the pipeline to transform them from continuous to discrete features; Frequent pattern mining algorithms are used to extract frequent feature combinations from discrete features; Multiple association rules are generated based on the frequent feature combinations obtained from mining. Each association rule is in the form of: IF{feature condition combination} THEN{risk correction value}, and the confidence, support and lift of each rule are calculated. Multiple association rules are filtered based on confidence, support, and lift to obtain an association rule library.

[0073] Optionally, the optimization unit 24 is specifically used for: The risk level is determined based on the ash blockage risk coefficient, and the risk levels include four levels: low risk, medium risk, high risk and extremely high risk. Select the corresponding basic oscillation mode based on the risk level; the basic oscillation modes include prevention mode, clearing mode and reinforcement mode; Based on the basic oscillation mode, the oscillation parameters are adjusted according to the physical characteristics of the pipeline; the oscillation parameters include oscillation frequency, oscillation intensity and oscillation duration.

[0074] Optionally, the multimodal sensors in the system include: an infrared thermal imager, an acoustic sensor, a vibration sensor, and a microwave humidity sensor. The multimodal sensors are integrated on an inspection platform that can move along the ash conveying pipeline, and the status monitoring of the entire length of the ash conveying pipeline is achieved through periodic inspections.

[0075] The control system provided in this application collects pipeline state data of the ash conveying pipeline through multi-modal sensors to obtain the pipeline's physical characteristics. These physical characteristics include multiple dimensions of state features. Based on the pipeline's physical characteristics and the type of ash in the pipeline, a basic risk coefficient for the ash conveying pipeline is determined. The basic risk coefficient is then corrected based on the rule matching results of the pipeline's physical characteristics in a constructed association rule base to obtain a blockage risk coefficient. When the blockage risk coefficient meets the set optimization conditions, the ash conveying pipeline undergoes oscillation strategy optimization. This method collects multiple dimensions of the ash conveying pipeline's state features, adaptively calculates the basic risk coefficient based on the ash type, and then introduces it into an association rule base for real-time pattern matching and risk correction. This enables accurate prediction of blockage risk and adaptive dynamic optimization of dust removal oscillation parameters. It significantly improves pipeline operational reliability, greatly reduces the risk of unplanned downtime and blockage clearing energy consumption, and forms a closed-loop intelligent maintenance system from state perception and intelligent diagnosis to precise control.

[0076] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0077] The above description is merely a specific implementation example of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0078] Secondly, those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0080] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0081] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0082] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0083] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0084] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0085] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0086] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for controlling the de-dusting shock of a fly ash pipeline, characterized by, The method comprises the following steps: acquiring pipeline physical characteristics by collecting pipeline state data of the ash conveying pipeline through a multi-modal sensor; wherein the pipeline physical characteristics include multiple dimensional state characteristics; determining a basic risk coefficient of the ash conveying pipeline according to the pipeline physical characteristics and the ash type in the ash conveying pipeline; correcting the basic risk coefficient according to a rule matching result of the pipeline physical characteristics in a constructed association rule library to obtain an ash blocking risk coefficient; when the ash blocking risk coefficient meets a set optimization condition, performing an oscillation strategy optimization on the ash conveying pipeline.

2. The method of claim 1, wherein, The pipeline physical characteristics include temperature state characteristics, acoustic state characteristics, vibration state characteristics, humidity state characteristics, and ash deposition thickness characteristics; and the pipeline state data of the ash conveying pipeline is collected through a multi-modal sensor to acquire the pipeline physical characteristics, which comprises the following steps: determining the temperature state characteristics according to a pipeline axial temperature gradient value and a pipeline circumferential temperature standard deviation in the pipeline state data; determining the acoustic state characteristics according to a frequency band energy value, an acoustic main frequency, a frequency spectrum kurtosis, and first, second, and third reference values corresponding to the frequency band energy value, the acoustic main frequency, and the frequency spectrum kurtosis respectively in the pipeline state data; determining the vibration state characteristics according to a vibration amplitude and an actual damping ratio of the pipeline at a natural frequency, and a reference amplitude and a reference damping ratio of a clean pipeline in the pipeline state data; determining the humidity state characteristics according to a volume moisture content and a critical moisture content threshold in the pipeline state data; determining the ash deposition thickness characteristics according to a thermal response time constant, a clean pipeline thermal response time constant, and a complete blocking thermal response time constant in the pipeline state data.

3. The method of claim 2, wherein, The method for determining the basic risk coefficient of the ash conveying pipeline according to the pipeline physical characteristics and the ash type in the ash conveying pipeline comprises the following steps: determining the basic risk coefficient of the ash conveying pipeline according to the temperature state characteristics, the acoustic state characteristics, the vibration state characteristics, the humidity state characteristics, and the ash type as a risk fault tolerance coefficient.

4. The method of claim 3, wherein, The method for correcting the basic risk coefficient according to the rule matching result of the pipeline physical characteristics in the constructed association rule library to obtain the ash blocking risk coefficient comprises the following steps: matching feature values of the temperature state characteristics, the acoustic state characteristics, the vibration state characteristics, the humidity state characteristics, and the ash deposition thickness characteristics with rule conditions in the association rule library; calculating a risk correction value corresponding to each rule that is successfully matched; wherein the risk correction value of each rule is determined based on a confidence level, a support level, and a promotion level of the rule; fusing the risk correction values of each rule to obtain an association rule correction term; nonlinearly fusing the association rule correction term and the basic risk coefficient to obtain the ash blocking risk coefficient; wherein the nonlinear fusion adopts the following formula: wherein, is a dusting risk coefficient, is a base risk coefficient, is a correction term for association rules, is a weight coefficient, is a Sigmoid activation function.

5. The method of claim 4, wherein, The method comprises the following steps: collecting historical operation data, which includes the pipeline physical characteristics in normal and various ash blocking states; Discretize the pipeline physical features to convert the pipeline physical features from continuous features to discrete features; Mine frequent feature combinations from the discrete features by using a frequent pattern mining algorithm; Generate a plurality of association rules based on the frequent feature combinations mined, each association rule being in the form of: IF {feature condition combination} THEN {risk correction value}, and calculate the confidence, support and lift of each rule; Screen the plurality of association rules according to the confidence, support and lift to obtain the association rule base.

6. The method of claim 4, wherein, The optimization of the shock strategy for the ash conveying pipeline comprises: Determine a risk level based on the ash plugging risk coefficient, the risk level comprising four levels of low risk, medium risk, high risk and extremely high risk; Select a corresponding basic shock mode according to the risk level; wherein the basic shock mode comprises a prevention mode, a removal mode and a reinforcement mode; Adjust shock parameters based on the pipeline physical features on the basis of the basic shock mode; wherein the shock parameters comprise a shock frequency, a shock intensity and a shock duration.

7. The method of claim 1, wherein, The multi-modal sensor comprises an infrared thermal imager, a sound wave sensor, a vibration sensor and a microwave humidity sensor, and is integrated on a patrol platform that can move along the ash conveying pipeline to realize state monitoring of the entire ash conveying pipeline through periodic patrol.

8. A dusting shock control system for a fly ash duct, characterized by, Comprise: An acquisition unit is configured to acquire pipeline state data of an ash conveying pipeline by a multi-modal sensor to obtain pipeline physical features; wherein the pipeline physical features comprise a plurality of dimensional state features; A determination unit is configured to determine a basic risk coefficient of the ash conveying pipeline according to the pipeline physical features and a type of ash in the ash conveying pipeline; A matching correction unit is configured to correct the basic risk coefficient to obtain an ash plugging risk coefficient according to a rule matching result of the pipeline physical features in the constructed association rule base; An optimization unit is configured to optimize a shock strategy for the ash conveying pipeline when the ash plugging risk coefficient meets a set optimization condition.

9. A dust shakeout control system for a fly ash duct according to claim 8, characterized in that, The acquisition unit is specifically configured to: Determine the temperature state feature according to a pipeline axial temperature gradient value and a pipeline circumferential temperature standard deviation in the pipeline state data; Determine the acoustic state feature according to a frequency band energy value, an acoustic main frequency frequency and a spectral kurtosis in the pipeline state data, and a first reference value, a second reference value and a third reference value corresponding to the frequency band energy value, the acoustic main frequency frequency and the spectral kurtosis respectively; Determine the vibration state feature according to a vibration amplitude of the pipeline at a natural frequency, an actual damping ratio, a clean pipeline reference amplitude and a reference damping ratio in the pipeline state data; Determine the humidity state feature according to a volume moisture content and a critical moisture content threshold in the pipeline state data; Determine the ash deposition thickness feature according to a thermal response time constant, a clean pipeline thermal response time constant and a complete plugging thermal response time constant in the pipeline state data.

10. The dust shakeout control system for a fly ash duct of claim 8, wherein, The determination unit is specifically configured to: According to the temperature state feature, the acoustic state feature, the vibration state feature, the humidity state feature and the ash deposit thickness feature, the ash type is taken as a risk fault tolerance coefficient to determine the basic risk coefficient of the ash conveying pipeline.

Images