Boiler piping model construction management method and system for vibration suppression processing

Abstract

The application provides a boiler pipeline model construction management method and system for vibration suppression processing, and belongs to the technical field of model construction, and specifically comprises the following steps: performing update processing on the construction target based on an update method, determining the monitoring results of the self-excited vibration data of different construction targets in different flow interval, combining the construction target data and the matching flow interval data of the boiler, and determining the operation and maintenance management strategy of the vibration monitoring equipment of the boiler, determining the operation and maintenance processing of the vibration monitoring equipment of different boilers based on the operation and maintenance management strategy, determining the construction management method of the vibration analysis model of the pipeline of the boiler according to the matching degree of the operation and maintenance processing data of the boiler and the self-excited vibration data in the construction target and the self-excited vibration data of the model, and improving the reliability of the self-excited vibration processing.

Description

Technical Field

[0001] This invention belongs to the field of model building technology, and in particular relates to a method and system for building and managing boiler pipeline models for vibration suppression. Background Technology

[0002] During operation, boiler pipes inevitably experience self-excited vibration. Existing technical solutions often involve constructing a boiler pipe model and using the simulation results of the model to generate corresponding suppression schemes for self-excited vibration. Therefore, the reliability of the simulation results is crucial to the vibration suppression results.

[0003] To address the aforementioned technical problems, for example, invention patent application CN202511504388.3, ​​"Analysis Method, System, and Computer-Readable Medium for Pipeline Acoustic Vibration," provides a similar technical solution, but it still has the following drawbacks: When constructing a self-excited vibration model, there may be a certain degree of deviation between the self-excited vibration model and the actual vibration state of the boiler pipeline. Therefore, it is an urgent technical problem to determine the construction and management strategy of the boiler pipeline model by combining operation and maintenance data and the degree of matching between the self-excited vibration model and the actual vibration state of the boiler pipeline, so as to determine the actual matching state of the model in different boilers and provide data reference for further optimization of the model.

[0004] To address the aforementioned technical problems, this application provides a method and system for constructing and managing boiler pipeline models for vibration suppression treatment. Summary of the Invention

[0005] To achieve the objectives of this invention, the following technical solution is adopted: Specifically, this application provides a boiler piping model construction and management method for vibration suppression treatment, which includes: S1 is a method for updating the construction target of the vibration analysis model of the boiler's pipeline based on the boiler's monitoring data, which determines the stable time period data of the boiler's pipeline in different flow ranges, and determines the matching flow range of the boiler based on the stable time period data. S2 updates the construction target based on the update method, determines the monitoring results of self-excited vibration data of different construction targets in different flow ranges, and determines the operation and maintenance management strategy of the vibration monitoring equipment of the boiler by combining the construction target data and the matching flow range data of the boiler. S3 performs operation and maintenance processing of vibration monitoring equipment for different boilers based on the operation and maintenance management strategy. Based on the boiler operation and maintenance processing data and the degree of matching between the self-excited vibration data in the construction target and the self-excited vibration data of the model, the construction management method of the vibration analysis model of the boiler pipeline is determined.

[0006] The beneficial effects of this invention are as follows: This paper proposes an update method for constructing vibration analysis models of boiler pipelines using boiler data belonging to matching flow ranges in different flow ranges. Considering the commonalities and individual differences in the self-excited vibration risk of multiple boilers of the same model, specifically taking into account the number of matching flow ranges that can be used for self-excited vibration analysis when constructing the boiler vibration analysis model, and the overlap between matching flow ranges and other boilers, which leads to differences in the reference value for self-excited vibration risk assessment of other boilers, this paper determines the update method for constructing vibration analysis models. This lays the foundation for determining the reliability of vibration analysis model processing in different matching flow ranges.

[0007] Based on the boiler's operation and maintenance data and the degree of matching between the self-excited vibration data in the target system and the self-excited vibration data in the model, the management method for constructing the vibration analysis model of the boiler's pipelines is determined. This fully considers that some boilers may not have triggered model updates (e.g., they haven't experienced self-excited vibration or haven't met update conditions), but their respective matched flow ranges may have two types of problems: First, the actual vibration data of other boilers in this range (i.e., the "target system") deviates significantly from the model predictions, indicating poor model reliability in this range; second, the monitoring equipment of some boilers in this range is abnormal (i.e., "monitoring abnormal boilers"), obstructing the natural update channel based on self-excited vibration and resulting in low update efficiency. These two types of problems together lead to uncertainty in the model reliability of this range, and it cannot rely on natural events for timely correction. Therefore, based on the severity of these problems in the matched flow range involved by the boiler, combined with the reliability of the boiler's own monitoring equipment, it is necessary to decide whether to actively initiate model construction for it and collect data under stable operation without self-excited vibration. This provides a reliable basis for model calibration for abnormal matched flow ranges, ensuring the timeliness and accuracy of model updates.

[0008] Furthermore, the monitoring data of the boiler is determined based on the flow rate of the boiler's pipes at different times.

[0009] Furthermore, the stable time period data within the flow range refers to the time period during which all monitoring times fall within the flow range.

[0010] Furthermore, the method for determining the matching flow range of the boiler is as follows: The stable time period within the flow range is determined using the stable time period data of the boiler in different flow ranges; Based on the stable periods within the flow range, stable periods with a duration greater than a preset duration threshold are determined and identified as periods of risk of self-excited vibration. Using the self-excited vibration risk period data within the flow range, determine whether the flow range belongs to the matching flow range of the boiler.

[0011] Furthermore, the method for determining the operation and maintenance management strategy of the boiler vibration monitoring equipment is as follows: S31 uses the monitoring results of the self-excited vibration data of the constructed target in different flow ranges to determine the flow range in which the constructed target has self-excited vibration data, and takes it as the self-excited vibration flow range. S32 determines the number of construction targets in different self-excited vibration flow ranges based on the construction target data; S33 uses the overlap data between the matching flow range and the self-excited vibration flow range of the boiler, as well as the number of construction targets for different self-excited vibration flow ranges, to determine the operation and maintenance management strategy of the boiler's vibration monitoring equipment.

[0012] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described method for constructing and managing a boiler pipeline model for vibration suppression processing when running the computer program.

[0013] Other features and advantages will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0014] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0015] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0016] Figure 1 This is a flowchart of a boiler piping model construction and management method for vibration suppression treatment; Figure 2 This is a flowchart illustrating the method for determining the matching flow range of a boiler; Figure 3This is a flowchart illustrating the method for determining the updating method of the construction target of the vibration analysis model of boiler piping. Detailed Implementation

[0017] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that the invention will be thorough and complete, and the concept of the exemplary embodiments will be fully conveyed to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore their detailed description will be omitted.

[0018] The terms “a,” “one,” “the,” and “the” are used to indicate the existence of one or more elements / components / etc.; the terms “including” and “having” are used to indicate an open-ended meaning of inclusion and that other elements / components / etc. may exist in addition to the listed elements / components / etc.

[0019] Example 1 To solve the above problems, according to one aspect of the present invention, such as Figure 1 As shown, a boiler piping model construction and management method for vibration suppression is provided, specifically including: S1 is a method for updating the construction target of the vibration analysis model of the boiler pipeline based on the boiler monitoring data, which determines the stable time period data of the boiler pipeline in different flow ranges, and determines the matching flow range of the boiler based on the stable time period data. S2 updates the construction target based on the update method, determines the monitoring results of self-excited vibration data of different construction targets in different flow ranges, and determines the operation and maintenance management strategy of the vibration monitoring equipment of the boiler by combining the construction target data and the matching flow range data of the boiler. S3 performs operation and maintenance processing of vibration monitoring equipment for different boilers based on the operation and maintenance management strategy. Based on the degree of matching between the self-excited vibration data and the self-excited vibration data of the model in different construction objectives, the construction management method of the boiler pipeline model of the boiler is determined.

[0020] Furthermore, the monitoring data of the boiler is determined based on the flow rate of the boiler's pipes at different times.

[0021] Furthermore, the stable time period data within the flow range refers to the time period during which all monitoring times fall within the flow range.

[0022] Specifically, such as Figure 2As shown, the method for determining the matching flow range of the boiler is as follows: To accurately identify which specific flow ranges during boiler operation may induce self-excited vibration in the piping system, these high-risk flow ranges are designated as "matched flow ranges." Self-excited vibration is a destructive vibration in a piping fluid system caused by fluid-structure interaction, and is usually related to specific flow conditions.

[0023] First, based on boiler operating data at different times, periods of stable operation (i.e., small flow fluctuations) are selected as the basis for analysis to ensure the effectiveness of subsequent analyses. Then, by setting duration thresholds, sufficiently long stable periods are further identified from these stable periods. Since self-excited vibration can only be sufficiently induced and sustained when a stable state lasts for a certain period, these periods are defined as "self-excited vibration risk periods." Finally, by evaluating the number or density of "self-excited vibration risk periods" within a flow range, it is determined whether that flow range belongs to a "matching flow range" that requires focused attention and avoidance.

[0024] S11 uses the stable time period data of the boiler in different flow ranges to determine the stable time period within the flow range; Flow range: refers to a series of continuous, non-overlapping numerical intervals into which the flow range of boiler pipelines is divided according to a preset step size. For example, the flow range of 0-1000 t / h can be divided into intervals of 50 t / h each.

[0025] Stable period data refers to the data set extracted from the historical operating data of the boiler, which corresponds to a continuous time period in which the instantaneous flow value at all monitoring times falls within the same specific flow range.

[0026] Stable period: refers to a continuous period of time in which traffic monitoring data at all times remains strictly within a certain traffic range.

[0027] The significance of dividing flow rates into "ranges" lies in transforming continuous data into discrete data, which facilitates a systematic examination of boiler behavior under different flow levels. Continuous flow data cannot be directly used to determine range attributes. By dividing the data into ranges, infinitely continuous operating states can be categorized into a finite number of manageable categories.

[0028] The significance of defining "stable period data" lies in filtering out the "pure" samples for analysis. Boiler operation often involves transitional conditions such as load fluctuations and start-ups / shutdowns. Data from these conditions is mixed with the influence of multiple flow ranges and cannot be used to analyze the inherent characteristics under a specific flow rate. Only by extracting data where the flow rate is stable within a certain range can interference be eliminated, ensuring that subsequent assessments of self-excited vibration risks are based on a single operating condition.

[0029] Identifying "stable time periods" is the core step in data preprocessing. It concretizes "stable time period data" through temporal continuity, connecting abstract data points into physically meaningful segments, laying the foundation for subsequent duration statistics.

[0030] To analyze the vibration risk of the low-temperature reheater tube panel of a 600MW boiler in a power plant within a flue gas flow rate range of 800-900 km³ / h, technicians first defined the flow rate range A = [800, 900) km³ / h. Subsequently, the system scanned one year's worth of historical boiler operating data and found that during the 30 minutes from 09:15:00 to 09:45:00 on April 12, 2024, the monitored values ​​of the flue gas flow rate at the tail flue flue fluctuated between 820 and 860 km³ / h every second, all falling within range A. Therefore, this 30-minute data set constitutes the "stable period data" within range A, and the time period from 09:15:00 to 09:45:00 on April 12, 2024, was identified as a "stable period" within flow rate range A.

[0031] S12 Based on the stable time period within the flow range, determine the stable time period within the flow range whose stable duration is greater than a preset duration threshold, and take it as the self-excited vibration risk period; Stable duration: refers to the length of time from the beginning to the end of an identified "stable period", usually measured in minutes or hours.

[0032] Preset duration threshold: This is a pre-set time value used to determine whether a stable period of time meets the "time conditions" for inducing self-excited vibration. It represents the shortest duration required for the Karman vortex street to form, develop, couple with the natural frequency of the tube screen, and finally excite significant vibration when flue gas laterally scours the tube bundle.

[0033] Self-excited vibration risk period: refers to a period of stable operation within a specific flue gas flow range that lasts long enough (i.e., stable duration > preset duration threshold) to have a sufficient chance of triggering and maintaining the stable operation of the tube screen self-excited vibration.

[0034] The significance of introducing "stabilization duration" lies in quantifying the cumulative effect of risk over time. Even if the flue gas flow briefly passes through a hazardous area, and that area itself possesses high-risk characteristics, the short duration may prevent the formation of a stable vortex shedding or sufficient coupling with the tube screen, thus avoiding destructive vibrations. Therefore, the time factor must be incorporated into the risk assessment system.

[0035] The significance of setting a "preset duration threshold" lies in introducing an engineering judgment criterion based on the fluid-structure interaction mechanism. This threshold is not arbitrarily set, but rather derived from the dynamic characteristics of the tube panel structure, the Strouhal number relationship of the flue gas lateral scour, and historical vibration accident experience. For example, if theoretical calculations or modal tests show that a certain type of boiler's low-temperature reheater tube panel needs to operate continuously for at least 20 minutes at dangerous flue gas flow rates to generate an amplitude sufficient to cause fatigue damage, then 20 minutes is a reasonable threshold.

[0036] The significance of defining "self-excited vibration risk periods" lies in upgrading "potential risks" to "actual risk samples." It signifies that we no longer focus on all periods of stable flue gas flow, but rather on those long-term stable operating segments that truly pose a threat to the safety of the heated surfaces. These segments serve as direct evidence for subsequent judgments of "matching flow ranges," demonstrating a crucial transformation from data to knowledge.

[0037] Continuing the previous example, within the flue gas flow range A [800, 900) km³ / h, in addition to the previously identified 30-minute stable period, another 12-minute stable period was detected, from 14:10:00 on 2024-05-20 to 14:22:00 on 2024-05-20. Based on the modal analysis report and historical vibration records of the boiler's low-temperature reheater tube panel, technicians set the "preset duration threshold" to 15 minutes. Therefore, the system will classify the first 30-minute stable period as a "self-excited vibration risk period" because it meets the condition that the flue gas flow rate is continuously stable within range A and the duration exceeds 15 minutes. The second 12-minute stable period, although also stable within range A, does not meet the "time condition" due to insufficient duration and is therefore not marked as a risk period.

[0038] S13 uses the self-excited vibration risk period data within the flow range to determine whether the flow range belongs to the matching flow range of the boiler.

[0039] It is understood that if the number of self-excited vibration risk periods within the flow range is greater than the preset number of risk periods, then the flow range is determined to belong to the matching flow range of the boiler.

[0040] Self-excited vibration risk period data: refers to all detailed information marked as "self-excited vibration risk period", including the timestamp of its occurrence, duration, corresponding flue gas flow fluctuation details, and amplitude changes of vibration measuring points during the period.

[0041] Matching flow range: This refers to the flue gas flow ranges that are ultimately identified and are highly correlated with the risk of self-excited vibration of the boiler's tail flue heating surface. When the boiler operates within these flue gas flow ranges, it is considered to have a higher risk of self-excited vibration, requiring operators to pay close attention or take measures such as combustion adjustment and load avoidance.

[0042] The significance of using "self-excited vibration risk period data" for judgment lies in achieving reliable decision-making based on statistical evidence. We do not rely on a single risk event that might be caused by accidental factors, but rather on the statistical regularities of long-term operational data. If, within a flue gas flow range, "self-excited vibration risk periods" that meet the time conditions and induce risk repeatedly occur, then the conclusion that this range has high-risk attributes has high statistical credibility and can effectively avoid misjudgments caused by a single abnormal operating condition.

[0043] Determining the "matching flow range" is the ultimate goal and core value of the entire analysis process. It completes the knowledge transformation from raw operating data to executable operating strategies. Through this step, we can create a "flue gas flow risk map" of the boiler tail flue, clearly identifying which flue gas flows are "dangerous areas" that need to be avoided. This provides scientific data support for optimizing boiler load distribution, developing vibration alarm strategies, and even modifying the heating surface structure.

[0044] The system continues to analyze all flue gas flow ranges. For flow range A = [800, 900) km³ / h, the system counted 8 instances of "self-excited vibration risk periods" (i.e., stable operating segments where the flue gas flow rate remained within the range for more than 15 minutes) in the past year's operating history. For flow range B = [600, 700) km³ / h, only one such instance occurred. According to the preset judgment rule, "when the annual cumulative number of self-excited vibration risk periods in a flue gas flow range reaches or exceeds 5, the range is determined to be a matched flow range," the system determines that flow range A is a "matched flow range," meaning that the boiler will face a high risk of self-excited vibration if it operates under this flue gas flow rate for a long period. Range B, however, is not considered a matched flow range.

[0045] Specifically, such as Figure 3 As shown, the method for determining the update method of the construction target of the vibration analysis model of the boiler pipeline is as follows: A dynamic and adaptive triggering strategy is developed for the construction and updating of the vibration analysis model of the boiler tail flue heating surface. Considering the commonalities and individual differences in the self-excited vibration risk of multiple boilers of the same model, specifically the number of matching flow ranges that can be used for self-excited vibration analysis when constructing the boiler vibration analysis model, and the overlap between these matching flow ranges and those of other boilers, leading to differences in the reference value for self-excited vibration risk assessment of other boilers, the update method for the construction target of the vibration analysis model is determined. This lays the foundation for determining the reliability of vibration analysis processing of the vibration analysis model within different matching flow ranges.

[0046] By analyzing the number of boilers associated with a specific "matching flow range" (i.e., the prevalence of the risk range within the boiler group) and the overlap between these boilers' matching flow ranges (i.e., the correlation of risk characteristics), a hierarchical decision tree is constructed. When the risk range is prevalent, sensitive triggering is used to capture common patterns. When most associated boilers within a risk range are also "reliable boilers" (i.e., they possess reliable update ranges), it indicates that these boilers can provide vibration events for model verification at a high frequency. In this case, stricter triggering conditions should be applied to them to ensure the validity of the vibration events. For individuals that are not reliable boilers, a relatively lenient update method can be used due to their lower verification value. When there is a high degree of overlap between risk ranges, sensitive triggering is used to achieve joint analysis. When risk characteristics are relatively isolated, personalized processing is performed based on the risk complexity of a single boiler. Through this hierarchical strategy, refined management from group commonalities to individual characteristics is achieved.

[0047] S21 uses boiler data belonging to the matching flow range in different flow ranges to determine the boilers belonging to the matching flow range in the matching flow range, and uses them as the associated boilers of the matching flow range. Matching traffic range: refers to the range of traffic matched through preceding steps (such as...). Figure 2 The method shown indicates the flue gas flow range with a high risk of self-excited vibration for a specific boiler.

[0048] Boiler data: Includes identification information for multiple boilers of the same model, historical operating data, and a list of their respective identified matching flow ranges.

[0049] Associated boilers: For a specific matching flow range (e.g., flue gas flow range X), all boilers that include range X as their own matching flow range are called associated boilers of range X.

[0050] The significance of establishing a "range-boiler" mapping relationship lies in extending the risk attribute from a single boiler to a group of boilers. By identifying how many boilers share each matching flow range, it is possible to preliminarily determine whether the risk range is a "personal problem" of an individual boiler or a "common problem" of most boilers.

[0051] The significance of defining "associated boilers" lies in constructing a dedicated set of boilers for each risk range, making subsequent analysis more focused and effective.

[0052] There are a total of 6 boilers of the same model (numbered #1 to #6). Through the previous analysis, a list of matching flow ranges was obtained for each boiler. For example, for the matching flow range A [800, 850) km³ / h, it appears in the lists of #1, #2, and #3. Therefore, the associated boilers for range A are #1, #2, and #3.

[0053] S22 determines the number of overlaps between the associated boilers in the matched flow range and other matched flow ranges based on the matched flow range of the associated boilers in the matched flow range. Other matching traffic ranges: refers to all matching traffic ranges other than the currently being analyzed matching traffic range.

[0054] Overlapping quantity: refers to the number of boilers that, in addition to the current matching flow range, also have at least one other matching flow range among all associated boilers in the current matching flow range.

[0055] The significance of introducing the "overlapping number" lies in assessing the "independence" of the current risk range and the complexity of boiler risk. A high overlapping number indicates that these boilers generally have multiple risk ranges, their risk characteristics are more complex, and they may contain information related to multiple ranges.

[0056] For the matching flow range A [800,850) km³ / h, its associated boilers #1, #2, and #3 all have other ranges (#1 has C, #2 has B, and #3 has D), with a total overlap of 3.

[0057] S23 is a method for updating the construction target of the vibration analysis model of the boiler pipeline by utilizing the associated boilers of the matched flow range and the number of overlaps between the associated boilers of the matched flow range and other matched flow ranges.

[0058] Specifically, the above steps include the following situations: Case 1: If the number of associated boilers in the matched flow range is greater than the preset threshold for the number of associated boilers, then as long as the associated boilers in the matched flow range experience self-excited vibration in any matched flow range, the vibration analysis model will be constructed.

[0059] Preset threshold for the number of associated boilers: an integer used to determine whether a certain risk range is "common" in the boiler group.

[0060] Vibration analysis model construction process: refers to initiating the model update process.

[0061] When a risk range is shared by a sufficient number of boilers, it indicates that self-excited vibration under this condition is a common phenomenon, and vibration events of any associated boilers contain common information, which should trigger an update.

[0062] Assume the threshold is 3. If there are 6 boilers with an interval E greater than 3 associated with each other, then any one of these 6 boilers will vibrate in any matching interval, thus triggering a model update.

[0063] Scenario 2: If the number of associated boilers in the matched flow range is not greater than a preset threshold for the number of associated boilers, the matched flow range in which vibration analysis model construction is performed as soon as vibration occurs in any matched flow range is taken as a reliable update range. The proportion of associated boilers in the matched flow range that have a reliable update range is determined by the number of overlaps between the associated boilers in the matched flow range and other matched flow ranges, and this proportion is taken as the reliable association ratio. If the reliable association ratio of the matched flow range is greater than a preset association ratio threshold, then the vibration analysis model construction is performed as soon as the duration of self-excited vibration in any matched flow range exceeds the target duration.

[0064] Reliable update interval: The matching flow interval that has been decided as "update upon vibration".

[0065] Reliable association ratio: The proportion of boilers in the current interval association whose own matching interval list contains at least one reliable update interval.

[0066] Preset correlation ratio threshold: A ratio used to determine whether the proportion of reliable boilers in the current interval is high enough.

[0067] Target duration: A time threshold used to measure the severity of a vibration event.

[0068] A high proportion of reliable correlations indicates that most of the correlated boilers in the current interval also have reliable update intervals. These boilers, due to their own frequently triggered update intervals, can frequently provide vibration events for model validation. Therefore, the timeliness of observing whether the model can accurately reflect the actual self-excited vibration situation is high—that is, every time these boilers vibrate and trigger an update, the predictive effect of the new model on the current interval and other correlated intervals can be quickly verified. Therefore, a more rigorous approach can be used to construct the model for unreliable boilers.

[0069] Assuming a threshold of 60% and a target duration of 2 hours, if there are 3 boilers (#6, #7, #8) associated with interval G, where #6 and #7 have a reliable update interval E, while #8 does not, the reliable association ratio is approximately 66.7% (2 / 3 > 60%). For #8 (the unreliable boiler), an update is only triggered if it experiences vibration in any matching interval for a total duration exceeding 2 hours.

[0070] Case 3: If the reliable correlation ratio of the matched flow range is not greater than the preset correlation ratio threshold, the proportion of associated boilers that overlap with other matched flow ranges is determined by the number of overlaps between the associated boilers in the matched flow range and other matched flow ranges. It is then determined whether the proportion of associated boilers that overlap with other matched flow ranges is greater than the preset ratio threshold. If so, the vibration analysis model is constructed as long as the associated boiler in the matched flow range experiences self-excited vibration in any matched flow range. If not, within the matched flow range, the update method for determining the associated boiler as the construction target of the vibration analysis model is determined based on the number of matched flow ranges of the associated boiler.

[0071] It should be noted that when the number of matching flow intervals of the associated boiler is greater than the preset threshold for the number of matching intervals, the vibration analysis model will be constructed as long as the associated boiler experiences self-excited vibration in any matching flow interval. Otherwise, the vibration analysis model will be constructed as long as the duration of self-excited vibration in any matching flow interval of the associated boiler exceeds the target duration.

[0072] The proportion of associated boilers that overlap with other matching flow ranges: that is, the proportion of overlapping boilers to the total number of associated boilers.

[0073] Preset ratio threshold: A ratio used to determine the degree of overlap between the current interval and other intervals.

[0074] When the reliable correlation ratio is not high, examine the degree of overlap between the current interval and other ordinary intervals. If the overlap ratio is high, it indicates that the associated boilers share common risks across multiple intervals, and a sensitive triggering method is used to achieve joint analysis; if the overlap ratio is low, individualized judgment is required.

[0075] Specific example: The overlap rate of interval A is 100% > 50%, which means that any individual that does not belong to a reliable boiler will trigger an update as soon as vibration occurs, thus achieving joint analysis.

[0076] Preset matching interval number threshold: an integer used to determine the risk complexity of a boiler. Subsequent personalized processing determines the trigger sensitivity based on the number of risk intervals of the boiler itself.

[0077] Specific example: Assuming a threshold of 3, boiler #6 has only one interval, then it is required that it vibrates in any matching interval and the total duration exceeds 2 hours before an update is triggered.

[0078] This technical solution provides a vibration monitoring equipment operation and maintenance management method based on the comparison of actual monitoring data and theoretical risks. Through hierarchical decision-making, limited operation and maintenance resources are concentrated on the range with low risk matching degree or the period that needs to be focused on, avoiding blind inspection and over-maintenance, and significantly improving operation and maintenance efficiency.

[0079] The basic operation and maintenance strategy ensures that the monitoring equipment is in good condition during operation in all high-risk areas, improving the reliability of vibration data; the target operation and maintenance strategy addresses the discrepancy between theoretical expectations and actual monitoring, helping to discover equipment failures or model defects.

[0080] This method is not only applicable to vibration monitoring of boiler tail flue, but can also be extended to the operation and maintenance management of monitoring systems for other industrial equipment, providing an effective tool for the construction of intelligent operation and maintenance systems.

[0081] Specifically, the method for determining the operation and maintenance management strategy of the boiler vibration monitoring equipment is as follows: A dynamic and scientific operation and maintenance management strategy should be developed for the vibration monitoring equipment on the heating surface of the boiler tail flue to ensure the reliability and measurement accuracy of the monitoring equipment. This will ensure that when self-excited vibration events occur, the vibration analysis model can be constructed and updated in a timely manner based on accurate monitoring data. Vibration monitoring equipment operates in harsh environments with high temperatures and high dust levels for extended periods, and its performance may degrade over time. Failure to maintain it in a timely manner will lead to distorted monitoring data, making it difficult to effectively manage risk when self-excited vibrations occur, thus reducing the efficiency of model updates. Therefore, it is necessary to intelligently determine when to perform operation and maintenance on the monitoring equipment based on the degree of matching between the actual monitored self-excited vibration and the theoretical risk range, as well as the number of boilers vibrating in each range (i.e., the number of target boilers). When the number of boilers actually vibrating in a theoretical risk range is small, it indicates that there is insufficient data for model validation in that range, and the reliability of the model's risk analysis in that range is low. In this case, the operation and maintenance of the monitoring equipment should be strengthened to ensure that once vibration occurs, the collected data can accurately reflect the real situation, providing a reliable basis for model updates. This will allow the model to be validated on more boilers, improving its generalization ability.

[0082] The core logic is as follows: First, based on actual monitoring data, identify which flue gas flow ranges actually experienced self-excited vibration, defining them as "self-excited vibration flow ranges." Then, count the number of boilers vibrating within each self-excited vibration flow range, i.e., the "number of targets." Next, compare the theoretical risk range (i.e., the "matching flow range") with the actual vibration ranges. Calculate the ratio of the number of boilers actually vibrating to the number of theoretically risky boilers within each matching flow range (i.e., the "target matching coefficient"). The lower this coefficient, the less sufficient the model validation is within that range, and the more reliable monitoring equipment is needed to capture future vibration data. Based on the number and proportion of these insufficient ranges, a tiered operation and maintenance management strategy is determined: when insufficient ranges are prevalent, comprehensive operation and maintenance (basic operation and maintenance strategy) is adopted; when insufficient ranges are few, targeted operation and maintenance (target operation and maintenance strategy) is adopted; when all ranges are sufficiently validated, no additional operation and maintenance is required. Through this tiered strategy, limited operation and maintenance resources are precisely invested in the most critical ranges requiring protection, ensuring that high-quality data can be obtained promptly when self-excited vibration occurs, for model construction and updates.

[0083] S31 uses the monitoring results of the self-excited vibration data of the constructed target in different flow ranges to determine the flow range in which the constructed target has self-excited vibration data, and takes it as the self-excited vibration flow range. Construction target: refers to the boiler body or its heated surface tube panel equipped with vibration monitoring equipment, which is the source of vibration data. In this scheme, each boiler can be regarded as an independent construction target.

[0084] Self-excited vibration data: refers to characteristic data such as vibration amplitude and frequency collected by vibration monitoring equipment and confirmed by analysis as self-excited vibration phenomena.

[0085] Self-excited vibration flow range: refers to the flow range within which at least one target device has experienced self-excited vibration, as statistically determined based on actual monitoring results.

[0086] The significance of defining the "self-excited vibration flow range" lies in linking theoretical risks with actual occurrences. The theoretical matching flow range is derived from historical data or mechanistic analysis, while actual vibration data reflects the true performance under current equipment conditions and operating parameters. Identifying the actual vibration range provides factual evidence for subsequent comparative analysis.

[0087] The significance of using "construction target" as the unit is that it can quantify the distribution of risk on different boilers, laying the foundation for subsequent statistics on the number of vibrating boilers in each interval, thereby evaluating the adequacy of the model's validation in each interval.

[0088] There are six boilers of the same model (numbered #1 to #6), and each boiler's tail flue is equipped with a vibration monitoring sensor. During the past 30 days of operation, the system recorded self-excited vibration events of each boiler under different flue gas flow rates. Statistical analysis showed that boilers #1 and #2 experienced self-excited vibration within flue gas flow rate range A [800, 850) km³ / h; boilers #2, #4, and #5 vibrated within range B [900, 950) km³ / h; boiler #1 vibrated within range C [1000, 1050) km³ / h; and no boilers vibrated within range D [1100, 1150) km³ / h. Therefore, the self-excited vibration flow rate ranges are determined to be A, B, and C.

[0089] S32 determines the number of construction targets in different self-excited vibration flow ranges based on the construction target data; Number of targets: refers to the number of boilers that have experienced self-excited vibration within a certain self-excited vibration flow range.

[0090] Counting the number of boilers within each actual vibration interval quantifies the prevalence of risk within that interval. More importantly, it reflects the data sample size used for model validation within that interval. If the number of boilers vibrating in a certain interval is small, it means that the model lacks sufficient actual data to support its risk predictions for that interval, and the reliability of its analysis results may be low. This information will be used to determine whether it is necessary to strengthen the operation and maintenance of monitoring equipment to ensure that accurate data can be obtained in the future.

[0091] According to the above monitoring results, there are 2 boilers (#1, #2) in the self-excited vibration flow range A, 3 boilers (#2, #4, #5) in the range B, and 1 boiler (#1) in the range C.

[0092] S33 uses the overlap data between the matching flow range and the self-excited vibration flow range of the boiler, as well as the number of construction targets for different self-excited vibration flow ranges, to determine the operation and maintenance management strategy of the boiler's vibration monitoring equipment.

[0093] Matching traffic range: refers to the range of traffic matched through prior analysis (such as...). Figure 2 The method identifies the flue gas flow ranges that theoretically pose a risk of self-excited vibration. Each matched flow range has its corresponding set of associated boilers.

[0094] Overlapping data: refers to the inclusion relationship between the matched flow range and the self-excited vibration flow range, that is, which matched ranges actually vibrated.

[0095] Constructing the target matching coefficient: For a given matching flow range, the target matching coefficient is defined as the ratio of the number of boilers that actually experience self-excited vibration within that range to the total number of associated boilers within that range. This coefficient reflects the density of actual vibration occurrences within the theoretical risk range. The lower the coefficient, the less data is available for model validation in that range, and the worse the reliability of the model analysis.

[0096] Other flow ranges: These refer to the flow ranges where the target matching coefficient is not greater than the preset matching coefficient threshold, i.e., the ranges where the theoretical risk and actual vibration have a low degree of agreement and the model validation is insufficient.

[0097] Basic operation and maintenance strategy: This refers to the comprehensive operation and maintenance (such as calibration and inspection) of the vibration monitoring equipment whenever the boiler operates within any matched flow range within the most recent preset time period, so as to ensure that the monitoring equipment is in a reliable state when operating in all theoretical risk ranges.

[0098] Targeted maintenance strategy: This refers to performing maintenance on monitoring equipment only when the boiler is running in other specific flow ranges within a recent preset time period, in order to concentrate resources on protecting critical ranges where model validation is insufficient.

[0099] No maintenance required: This means that no additional maintenance operations are required for the monitoring equipment during the current assessment period.

[0100] By comparing the overlap between theoretical risks and actual vibrations, the accuracy of the theoretical model and the effectiveness of the monitoring equipment can be assessed. More importantly, by constructing target matching coefficients, it is possible to identify which theoretical risk intervals lack sufficient actual vibration data support. These intervals are precisely where the reliability of the model analysis is lower and requires special attention. The reliability of the monitoring equipment is particularly critical in these intervals because, once vibration occurs, the accuracy of the data must be ensured for model updates.

[0101] The hierarchical decision-making logic (cases 1-4) aims to dynamically adjust the investment of operation and maintenance resources based on the sufficiency of model validation: when all theoretical intervals are fully validated by actual vibrations, the model is reliable and can maintain routine operation and maintenance; when some intervals are not validated, the decision is made based on the proportion of the number of inadequate intervals to decide whether to strengthen operation and maintenance across the board or only strengthen operation and maintenance for specific intervals, thereby ensuring the quality of model update data while avoiding unnecessary operation and maintenance costs.

[0102] Specifically, if the matching flow range of the boiler is within the self-excited vibration flow range, then the operation and maintenance management strategy of the boiler vibration monitoring equipment is determined as the basic operation and maintenance strategy. That is, when there is a running period within the matching flow range in the most recent preset time period, the operation and maintenance of the boiler vibration monitoring equipment is carried out.

[0103] Determine whether all matched traffic intervals belong to the self-excited vibration traffic interval. If so, adopt the basic operation and maintenance strategy. This means that all theoretical risk intervals have actually experienced vibration. Adopting the basic operation and maintenance strategy can ensure the timeliness of updates when self-excited vibration occurs, achieve reliable verification of all matched traffic intervals, and comprehensively ensure the reliability of the monitoring equipment in all intervals.

[0104] Additionally, it is understood that if the matching flow range of the boiler does not uniformly fall within the self-excited vibration flow range, the following content is also included: Case 1: If there is no self-excited vibration flow range within the matching flow range of the boiler, then the operation and maintenance management strategy of the vibration monitoring equipment of the boiler is determined to be no operation and maintenance required. In this case, "there is no self-excited vibration flow range within the matched flow range" means that no self-excited vibration events were detected in any theoretically high-risk flue gas flow ranges during actual operation.

[0105] When no actual vibrations occur in any of the matched traffic intervals, there is no need to guarantee the critical reliability of the matched traffic interval model, and therefore no maintenance is required at this time. This avoids unnecessary maintenance during periods of no vibration, saving resources.

[0106] Continuing the previous example, assume there is one matching traffic interval D, and none of these intervals contain a target (i.e., the self-excited vibration traffic interval is empty). Since there is no self-excited vibration traffic interval within the matching traffic intervals, the maintenance strategy is determined to be no maintenance required. Operators do not need to perform additional checks on the monitoring equipment; further evaluation can be conducted after subsequent accumulation of operational data.

[0107] Case 2: If a self-excited vibration flow range exists within the matching flow range of the boiler, the matching coefficient of the construction target of the matching flow range is determined based on the ratio of the number of construction targets belonging to the self-excited vibration flow range within the matching flow range to the number of boilers belonging to the matching flow range within the matching flow range. If the matching coefficient of the construction target of the matching flow range of the boiler is greater than the preset matching coefficient threshold, then the operation and maintenance management strategy of the vibration monitoring equipment of the boiler is determined to be no operation and maintenance required. Construct target matching coefficients: As mentioned above, these reflect the proportion of boilers that actually vibrate within each theoretical risk range.

[0108] Preset matching coefficient threshold: A pre-defined proportional value used to determine whether the model has been sufficiently validated in this interval. When the coefficient is greater than the threshold, it is considered that there are enough actual vibration samples in this interval, and the model analysis is highly reliable.

[0109] When a sufficient number of boilers actually vibrate in each theoretical risk range (i.e., the coefficient is high), it indicates that the model's predictions in these ranges have been fully validated, the monitoring equipment has successfully captured the vibration events, and the equipment is functioning normally. In this case, the model's risk analysis for the corresponding range has a high degree of reliability, and no additional maintenance of the monitoring equipment is required. Therefore, no maintenance is necessary; maintaining the normal operating conditions is sufficient.

[0110] Assume that the associated boilers in the matching flow ranges A, B, and C are 3, 3, and 2 respectively. In actual monitoring, the coefficient for range A is 0.667, the coefficient for range B is 0.75, and the coefficient for range C is 0.5. All coefficients are not greater than the preset threshold of 0.7, therefore, we switch to scenario 3.

[0111] Case 3: If the target matching coefficient of the matching flow range of the boiler is not greater than the preset matching coefficient threshold, the matching flow range with the target matching coefficient not greater than the preset matching coefficient threshold will be used as other flow ranges. If the proportion of other flow ranges in the matching flow range of the boiler is greater than the preset range proportion threshold, then the operation and maintenance management strategy of the vibration monitoring equipment of the boiler will be determined as the basic operation and maintenance strategy. Other flow ranges: These refer to the flow ranges where the target matching coefficient is not greater than the preset matching coefficient threshold, i.e., the ranges where there are insufficient actual vibration samples and the model validation is inadequate.

[0112] Percentage of other traffic ranges: The proportion of other traffic ranges to the total number of all matched traffic ranges.

[0113] Preset interval proportion threshold: A pre-set proportion threshold used to determine whether intervals with insufficient model validation are dominant.

[0114] Basic operation and maintenance strategy: Within the most recent preset time period, as long as the boiler is operating within any matching flow range, comprehensive operation and maintenance will be carried out on the vibration monitoring equipment.

[0115] When a high percentage of intervals with insufficient model validation (exceeding a threshold) indicates that most intervals lack sufficient actual vibration data to support their validity, resulting in poor overall model reliability. In such cases, if vibration occurs in these intervals, it is crucial to ensure that monitoring equipment can accurately collect data for model updates. Therefore, it is necessary to comprehensively strengthen the operation and maintenance of monitoring equipment across all matching traffic intervals, employing basic maintenance strategies to improve the reliability of data capture.

[0116] As in the previous example, assuming that in the boiler's matching intervals A, C, and B, the coefficients are 0.667 for A, 0.5 for C, and 0.75 for B, and the other flow intervals are A and C (2 in total), accounting for 66.7%, which is greater than the preset percentage threshold of 50%, a basic operation and maintenance strategy is adopted. Within the first 30 days, if the boiler operates in any of the intervals A, C, or B, the operation and maintenance of the boiler monitoring equipment will be triggered.

[0117] Scenario 4: If the proportion of other flow ranges within the matched flow range of the boiler is not greater than the preset range proportion threshold, determine whether there are other flow ranges within the matched flow range of the boiler that do not require basic operation and maintenance processing. If so, determine the operation and maintenance management strategy of the boiler's vibration monitoring equipment as the target operation and maintenance strategy, that is, when there is a running segment in other flow ranges within the most recent preset time period, perform operation and maintenance processing on the boiler's vibration monitoring equipment. If not, determine the operation and maintenance management strategy of the boiler's vibration monitoring equipment as no operation and maintenance processing required.

[0118] Other traffic segments not covered by basic operations and maintenance (O&M) policies: These refer to traffic segments that are not currently covered by basic O&M policies. In scenario 4, since other traffic segments account for a small percentage and basic O&M policies have not been activated, these other traffic segments are essentially in an "unmaintained" state and require special attention.

[0119] Target maintenance strategy: Within the most recent preset time period, maintenance will only be performed on the monitoring equipment when the boiler is running in other specific flow ranges (i.e., ranges where model validation is insufficient), and maintenance will not be triggered when the boiler is running in other ranges.

[0120] When the proportion of insufficiently validated intervals for the boiler model is small (not exceeding a threshold), it indicates that most intervals have been sufficiently validated, with only a few intervals having insufficient sample size. In this case, comprehensive maintenance is unnecessary; instead, a targeted maintenance strategy should be adopted to ensure that monitoring equipment is in good condition during their operation, so as to promptly capture potential vibration events for model updates. If these critical intervals do not actually exist (e.g., all intervals have been sufficiently validated, but case 2 has been ruled out), then no maintenance is required.

[0121] A specific example: Assume boiler B has two matching flow intervals, B and D. In actual monitoring, the coefficient for B is 0.75, and the coefficient for D is 0, not exceeding 0.7. For boiler B, the other flow interval is D, which is 1 interval, accounting for 50%, equal to the preset threshold (assuming the threshold is 50%, then it is not greater than). Since there is another flow interval D, and no boilers in it fall under the basic maintenance strategy, the target maintenance strategy is adopted: within the first 30 days, maintenance is only performed on the monitoring equipment when the boiler is operating within interval D.

[0122] Furthermore, the method for determining the construction and management method of the boiler piping model is as follows: The core decision-making objective of this technical solution is to develop a dynamic and scientific pipeline model building management method for boilers whose model building has not yet been initiated (i.e., "boilers without model building"), to determine under what conditions model building should be proactively initiated for these boilers. In actual operation, some boilers may not have triggered model updates (e.g., they have not yet experienced self-excited vibration or met update conditions), but their respective matched flow ranges may have two types of problems: First, the actual vibration data of other boilers in this range (i.e., "build targets") deviates significantly from the model predictions, indicating poor model reliability in this range; second, the monitoring equipment of some boilers in this range is malfunctioning (i.e., "monitoring malfunctioning boilers"), obstructing the natural update channel based on self-excited vibration and resulting in low update efficiency. These two types of problems together lead to uncertainty in the model reliability of this range, and it cannot be corrected in a timely manner by relying on natural events. Therefore, it is necessary to determine whether to proactively initiate model building for these boilers based on the severity of these problems in the matched flow ranges they involve, combined with the reliability of the boiler's own monitoring equipment, and to collect data under stable operating conditions without self-excited vibration. This provides a reliable basis for model calibration for malfunctioning matched flow ranges, ensuring the timeliness and accuracy of model updates.

[0123] The core logic is as follows: First, identify boilers with unreliable monitoring equipment (monitoring abnormal boilers) based on operation and maintenance data. Second, identify boilers with significant model deviations by comparing actual self-excited vibration data with model predictions (matching deviation construction targets). Then, for each boiler that has not yet undergone model construction, analyze all its matching flow intervals, sequentially determining whether a matching deviation construction target exists, whether a matching deviation flow interval exists, whether all matching intervals are overlapping deviation intervals, the degree of clustering of monitoring abnormal boilers within overlapping deviation intervals, and combining this with the boiler's own abnormal operation and maintenance situation to make a tiered decision on whether to initiate proactive model construction. Through this tiered strategy, limited modeling resources are prioritized for boilers and intervals with the most prominent problems, improving the overall reliability of the model.

[0124] S41 determines the number of times the boiler's vibration monitoring equipment has abnormal operation and maintenance based on the boiler's operation and maintenance data, and uses this number as the abnormal operation and maintenance count to identify the boilers with abnormal monitoring. Operation and maintenance processing data: refers to the historical records of maintenance, calibration, and repair operations performed on vibration monitoring equipment, including the time, type, and whether any abnormalities were found for each operation and maintenance.

[0125] Abnormal maintenance frequency: Within the statistical period, the number of maintenance operations that recorded the vibration monitoring equipment as having abnormalities (such as sensor drift, signal interruption, loose installation, etc.).

[0126] Monitoring abnormal boilers: These refer to boilers whose abnormal maintenance occurrences fall within a preset range as a percentage of total maintenance occurrences. This range is used to define which boilers have significant reliability issues with their monitoring equipment, and is typically set to a reasonable range, such as 5%. Boilers exceeding this range are considered abnormal boilers. These boilers are actually discovered during maintenance, not those identified by the model.

[0127] The significance of defining "abnormal maintenance frequency" lies in quantifying the health status of monitored equipment. Each abnormal maintenance operation suggests potential performance degradation or malfunction of the equipment, and the accumulation of these events can affect the accuracy of subsequent monitoring data.

[0128] The significance of defining "monitoring abnormal boilers" lies in filtering out boilers whose data reliability is questionable. Their vibration data cannot be used as a valid basis for model construction and will slow down the update efficiency of self-excited vibration-based data for their respective intervals. By using a proportional interval rather than simply the number of cycles, the influence of differences in the operation and maintenance frequency of different boilers can be eliminated, making the judgment more equitable.

[0129] Specific examples: Statistics on the operation and maintenance data of each boiler over the past year: #3: 12 operation and maintenance operations, 1 anomaly, a rate of 8.3%. The preset rate range is set to [above 5%], meaning boilers with an anomaly rate above 5% are considered monitoring abnormal boilers. Therefore, boiler #3's rate of 8.3% falls within this range, making it a monitoring abnormal boiler; the remaining boilers are outside this range and are considered monitoring normal boilers.

[0130] S42 determines the construction targets whose matching degree does not meet the requirements in different matching flow ranges by using the degree of matching between the self-excited vibration data in the construction target and the self-excited vibration data in the model, and uses them as matching deviation construction targets. Construction targets: These refer to boilers equipped with vibration monitoring devices, with each boiler constituting a construction target. These boilers serve as the foundational data source for model validation and updates.

[0131] Self-excited vibration data: The actual monitored characteristic values ​​of self-excited vibration, such as vibration amplitude and dominant frequency.

[0132] Self-excited vibration data of the model: Vibration characteristic values ​​that should occur under the same flow range, predicted by existing vibration analysis models.

[0133] Matching degree: It is usually measured by error indicators (such as relative error, root mean square error). When the error exceeds the preset threshold, the matching degree is considered to be unsatisfactory.

[0134] Matching deviation is defined as a boiler whose actual vibration data deviates significantly from the model's predictions within a certain matched flow range. These deviations reflect the model's predictive failure for that boiler.

[0135] Comparing actual self-excited vibration data with model predictions can directly identify areas where the model has failed. If a boiler experiences repeated vibrations within a certain flow range but the model predictions are inaccurate, it indicates that the model needs to be modified for that boiler and that specific flow range.

[0136] Assuming the model predicts a vibration amplitude of 10 mm / s within the matched flow rate range [800, 850) km³ / h, the actual monitored vibration amplitude was 15 mm / s for boiler #1, 11 mm / s for boiler #2, and no vibration for boiler #3. Setting the matching deviation threshold to a relative error of 30%, boiler #1 has an error of 50% > 30%, which serves as the target for the matching deviation; boiler #2 has an error of 10% < 30%, which is not a deviation target. Similarly, statistics are performed in intervals B and C to obtain a list of boilers with deviations in each interval.

[0137] S43 constructs a target based on the matching deviation in different matching flow ranges and abnormal monitoring boiler data, and determines the construction and management method of the boiler pipeline model based on the number of abnormal operation and maintenance of the boiler.

[0138] Boilers for which no model has been built: This refers to boilers that have not yet been triggered for model building or updating within the current evaluation period. These boilers may be due to the absence of self-excited vibration or failure to meet the conditions of the original update strategy.

[0139] Matching traffic range: refers to the range of traffic matched through prior analysis (such as...). Figure 2 The method determines the flue gas flow range that theoretically carries the risk of self-excited vibration. Each boiler has its corresponding set of matching flow ranges.

[0140] Matching deviation construction target: determined by S42, reflecting the deviation of the model on a specific boiler.

[0141] Abnormal boilers: identified by S41, indicating boilers whose monitoring equipment is unreliable.

[0142] Matching Deviation Ratio: For a certain matching flow range, the ratio of the number of matching deviation targets within that range to the total number of associated boilers in that range.

[0143] Preset deviation ratio threshold: A pre-defined ratio value used to determine whether model deviation is prevalent in a certain range. When the matching deviation ratio is greater than this threshold, the range is called the "matching deviation flow range".

[0144] Overlap deviation range: refers to the ranges that are determined to be the flow ranges with matching deviation.

[0145] Anomaly monitoring ratio: For a given overlap deviation interval, this is the proportion of boilers with monitoring anomalies within that interval to the total number of associated boilers in that interval (including all associated boilers in the calculation). This ratio reflects the severity of the obstruction to natural renewal in that interval.

[0146] Sum of monitoring anomaly proportions: The value obtained by adding up the monitoring anomaly proportions of all overlapping deviation intervals of the current boiler.

[0147] Preset abnormal threshold: A pre-set value used to determine whether the degree of clustering of abnormal boilers within the overlap deviation range is too high.

[0148] Preset conditions: refers to "no abnormal maintenance occurrences within the recent preset time period", meaning that the boiler's own monitoring equipment has been operating normally and the data is reliable recently.

[0149] The second preset condition is: "There are no abnormal maintenance times in the most recent preset time period, and the proportion of the boiler's historical abnormal maintenance times to the total maintenance times is less than the abnormal proportion threshold". In other words, the boiler is not only normal in the near future, but its historical status has also been stable for a long time.

[0150] For boilers that have not been modeled, there may not be direct evidence that they need to be updated yet. However, if there are model deviations or monitoring anomalies of other boilers in the same range, it means that the overall model reliability of that range has decreased. Therefore, it is necessary to actively build a model for this boiler in order to verify the model under non-vibration conditions and lay the foundation for future model optimization.

[0151] By using multi-level judgment (whether there is a deviation target, whether there is a deviation range, whether there is a deviation across the entire range, and monitoring the degree of abnormal clustering), the severity of the problem can be quantified, thereby enabling tiered decision-making: if the problem is widespread and serious, proactive construction can be initiated immediately; if the problem is localized and minor, natural events can be waited for or a lenient strategy can be adopted.

[0152] At the same time, the current status of the boiler's own monitoring equipment must be considered to ensure that the data source used for construction is reliable and to avoid erroneous updates due to equipment problems.

[0153] It should be noted that the abnormal boilers mentioned are boilers whose abnormal maintenance frequency accounts for a proportion of the total maintenance frequency within a preset range.

[0154] Furthermore, based on the matching deviation within different matching flow ranges, a target is constructed, along with abnormal boiler monitoring data, and combined with the number of abnormal operation and maintenance operations of the boiler, a method for constructing and managing the boiler piping model is determined, specifically including: S431 Determine whether the boiler belongs to the abnormal monitoring boiler. If not, proceed to step S432. If not, the monitoring reliability of its vibration operation data is not good, so it cannot provide enough effective dataset for model construction. Therefore, the construction management method of the boiler pipeline model of the boiler is determined to still use the update method of the construction target of the vibration analysis model of the boiler pipeline to carry out the construction processing of the vibration analysis model. If the boiler's monitoring equipment is malfunctioning, all its data (including operating data under non-vibration conditions) is unreliable and cannot be used for model building. Therefore, active model building should be suspended until the equipment is repaired.

[0155] Specific handling: If the current boiler is a monitored abnormal boiler, the model building and management method is determined as follows: do not perform any active model building for the time being. At the same time, mark the boiler as pending observation. Otherwise, proceed to the next step.

[0156] S432 determines whether there is a matching deviation construction target in the matching flow range of the boiler. If yes, proceed to step S433. If no, determine that the construction management method of the boiler pipeline model is still to use the update method of the construction target of the vibration analysis model of the boiler pipeline to carry out the construction processing of the vibration analysis model. If the model predictions for the current boiler match the actual self-excited vibrations in all matching flow ranges (i.e., it is not the target for matching deviation construction), it means that the model is accurate for the boiler and does not need to be actively constructed; the original update method can be used.

[0157] If there is no matching deviation to construct the target (i.e., the current boiler has no deviation in all matching intervals), then the model construction management method for this boiler is determined to be: still using the original self-excited vibration-based update method for model construction. If there is a deviation, proceed to the next step.

[0158] S433 determines the matching deviation ratio of the matching flow range by using the proportion of the matching deviation of the construction target in the matching flow range. The matching flow range with the matching deviation ratio greater than the preset deviation ratio threshold is taken as the matching deviation flow range. It is determined whether there is a matching deviation flow range in the matching flow range of the boiler. If yes, proceed to step S434. If no, it is determined that the construction management method of the boiler pipeline model is still to use the update method of the construction target of the vibration analysis model of the boiler pipeline for vibration analysis model construction processing. If the deviation occurs only in a few boilers (low proportion), it may be an individual problem and can still be addressed by natural updates; if the deviation is widespread (high proportion), the model may fail as a whole in that range and requires close attention.

[0159] Specific processing: Calculate the matching deviation ratio for all matching flow intervals of the current boiler (the numerator is the number of target objects constructed by all deviations within that interval). If there are no matching deviation flow intervals (i.e., the deviation ratio of all intervals is ≤ the threshold, for example, 0.3), then the management method is determined to be: continue using the original update method. If they exist, proceed to the next step.

[0160] S434 takes the matching deviation flow range in the matching flow range of the boiler as the overlapping deviation range, and determines whether the matching flow range of the boiler belongs to the overlapping deviation range. If so, when the number of abnormal operation and maintenance of the boiler meets the preset condition, that is, when there is no abnormal operation and maintenance within the recent preset time, the boiler pipeline model is constructed. If not, proceed to step S435. If there is a general deviation in all matching intervals, it indicates that the model is in overall failure and the construction requirement is the highest. That is, when the monitoring data of the boiler confirms that the operation is reliable, the model construction process is carried out to achieve severe processing of the model.

[0161] If so, further determine whether the current number of abnormal maintenance operations of the boiler meets the preset conditions (i.e., there have been no abnormal maintenance operations in the most recent six months). If it meets the conditions, trigger model building (which can be started after comparative analysis under stable operating conditions); if it does not meet the conditions, do not build the model for now, and wait for the equipment to stabilize before evaluating it. If not (i.e., not all intervals are overlapping deviation intervals), proceed to the next step.

[0162] S435 determines the monitoring anomaly ratio of the overlapping deviation interval by removing the proportion of monitored abnormal boilers in the boiler of the construction target in different overlapping deviation intervals, and judges whether the sum of the monitoring anomaly ratios of the overlapping deviation intervals of the boiler is greater than a preset anomaly threshold. If so, it means that the overlapping deviation interval may be due to the presence of monitored abnormal boilers, which on the one hand leads to a slow update efficiency of the model construction target, and on the other hand, there is a situation where the matching degree of the simulation results of the model is poor. Therefore, when the number of abnormal operation and maintenance of the boiler meets the preset condition, that is, when there is no abnormal operation and maintenance in the recent preset period, the boiler pipeline model is constructed. If not, when the number of abnormal operation and maintenance of the boiler meets the second preset condition, that is, when there is no abnormal operation and maintenance in the recent preset period and the proportion of the abnormal operation and maintenance in the operation and maintenance is less than the anomaly ratio threshold, the boiler pipeline model is constructed.

[0163] "The proportion of boilers with abnormal monitoring among boilers excluding those with the target" may refer to the proportion of boilers with abnormal monitoring among other boilers besides those with the target in each overlap deviation interval, and then these proportions are summed to obtain the sum.

[0164] If there are many abnormal boilers within the overlap deviation range, the natural update channel will be severely blocked. Even if the model deviation is widespread, it will be difficult to correct it in a timely manner through self-excited vibration events. Therefore, active modeling is required. However, active modeling must ensure the reliability of the data source, so it needs to be combined with the timeliness of the equipment.

[0165] If the sum is greater than the preset anomaly threshold, it indicates a high degree of clustering of abnormal boilers within the overlap deviation interval, resulting in low update efficiency. In this case, if the number of abnormal maintenance operations for the current boiler meets the preset conditions (i.e., no abnormal maintenance operations within the recent preset time period), model construction is triggered; otherwise, construction is not performed.

[0166] If the sum is not greater than the preset anomaly threshold, it indicates that there are relatively few abnormal boilers monitored within the overlap deviation range, and the natural update channel is basically unobstructed, but there are still deviations. In this case, a medium demand strategy can be adopted: if the number of abnormal maintenance operations of the current boiler meets the second preset condition (i.e., there are no abnormal maintenance operations within the most recent preset period and the historical anomaly ratio is less than the anomaly ratio threshold), then model construction is triggered; otherwise, the original update method is still used.

[0167] As in the previous example, suppose that in the matching intervals A, C, and B of the boilers, interval A contains two boilers besides the target boiler, and there is one boiler under abnormal monitoring. That is, the abnormal monitoring ratio of the overlapping deviation interval in interval A is 0.5. Similarly, the ratio for interval B is 0.3, and interval C does not belong to the overlapping deviation interval. In this case, the sum of the two is 0.8, which is greater than the threshold of 0.6. Therefore, the basic operation and maintenance strategy is adopted. Model construction is carried out when there are no abnormal operation and maintenance times in the most recent six months. In other cases, in addition to the absence of abnormal operation and maintenance times in the most recent six months, the proportion of abnormal operation and maintenance times of the boiler in the total operation and maintenance times must be less than 0.1 before model construction can be carried out.

[0168] Example 2 Secondly, the present invention provides a power outage detection device applied to the aforementioned boiler pipeline model construction and management method for vibration suppression, specifically including: Identification module, associated fault determination module, analysis module; The identification module is responsible for determining the identification method for manually maintained users among the users; The associated fault determination module is responsible for determining the associated fault types of different detection risk fault types. The analysis module is responsible for determining the boiler pipeline model construction and management method for vibration suppression treatment in different users for the detected risk fault types.

[0169] Example 3 Thirdly, the present invention provides a sensing device disposed in the aforementioned power outage detection device, specifically comprising: Responsible for collecting and processing users' electricity consumption data.

[0170] Specifically, the electricity consumption data includes voltage, current, and power factor.

[0171] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0172] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0173] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for constructing and managing boiler piping models for vibration suppression treatment, characterized in that, Specifically, it includes: Based on the monitoring data of the boiler, the stable time period data of the boiler pipeline in different flow ranges are determined. Based on the stable time period data, the matching flow range of the boiler is determined. Based on the boiler data belonging to the matching flow range in different flow ranges, the method of updating the construction target of the vibration analysis model of the boiler pipeline is determined. Based on the update method, the construction target is updated to determine the monitoring results of self-excited vibration data of different construction targets in different flow ranges. Combined with the construction target data and the matching flow range data of the boiler, the operation and maintenance management strategy of the vibration monitoring equipment of the boiler is determined. Based on the aforementioned operation and maintenance management strategy, the operation and maintenance of vibration monitoring equipment for different boilers are carried out. According to the boiler operation and maintenance data and the degree of matching between the self-excited vibration data in the construction target and the self-excited vibration data of the model, the construction and management method of the vibration analysis model of the boiler pipeline is determined.

2. The boiler piping model construction and management method for vibration suppression treatment as described in claim 1, characterized in that, The monitoring data for the boiler is determined based on the flow rate of the boiler's pipes at different times.

3. The boiler piping model construction and management method for vibration suppression treatment as described in claim 1, characterized in that, The stable time period data within the flow range refers to the time period during which all monitoring times fall within the flow range.

4. The boiler piping model construction and management method for vibration suppression treatment as described in claim 1, characterized in that, The method for determining the matching flow range of the boiler is as follows: The stable time period within the flow range is determined using the stable time period data of the boiler in different flow ranges; Based on the stable periods within the flow range, stable periods with a duration greater than a preset duration threshold are determined and identified as periods of risk of self-excited vibration. Using the self-excited vibration risk period data within the flow range, determine whether the flow range belongs to the matching flow range of the boiler.

5. The boiler piping model construction and management method for vibration suppression treatment as described in claim 4, characterized in that, If the number of self-excited vibration risk periods within the flow range exceeds the preset number of risk periods, then the flow range is determined to belong to the matching flow range of the boiler.

6. The boiler piping model construction and management method for vibration suppression treatment as described in claim 1, characterized in that, The method for determining the operation and maintenance management strategy of the boiler vibration monitoring equipment is as follows: S31 uses the monitoring results of the self-excited vibration data of the constructed target in different flow ranges to determine the flow range in which the constructed target has self-excited vibration data, and takes it as the self-excited vibration flow range. S32 determines the number of construction targets in different self-excited vibration flow ranges based on the construction target data; S33 uses the overlap data between the matching flow range and the self-excited vibration flow range of the boiler, as well as the number of construction targets for different self-excited vibration flow ranges, to determine the operation and maintenance management strategy of the boiler's vibration monitoring equipment.

7. The boiler piping model construction and management method for vibration suppression treatment as described in claim 6, characterized in that, If the matching flow range of the boiler is within the self-excited vibration flow range, then the operation and maintenance management strategy of the boiler vibration monitoring equipment is determined as the basic operation and maintenance strategy. That is, when there is a running period within the matching flow range in the most recent preset time period, the operation and maintenance of the boiler vibration monitoring equipment is carried out.

8. The boiler piping model construction and management method for vibration suppression treatment as described in claim 7, characterized in that, If the matching flow range of the boiler does not all belong to the self-excited vibration flow range, or if there is no self-excited vibration flow range within the matching flow range of the boiler, then the operation and maintenance management strategy for the vibration monitoring equipment of the boiler is determined to be no operation and maintenance required.

9. The boiler piping model construction and management method for vibration suppression treatment as described in claim 1, characterized in that, The method for determining the construction and management method of the boiler piping model is as follows: Based on the boiler's operation and maintenance data, determine the number of times the boiler's vibration monitoring equipment has abnormal operation and maintenance, and use these abnormal operation and maintenance numbers to identify boilers with abnormal monitoring. Based on the degree of matching between the self-excited vibration data in the target and the self-excited vibration data in the model, the target that does not meet the matching requirements in different matching flow ranges is identified and used as the matching deviation target. Based on the matching deviation in different matching flow ranges, the target is constructed, and the abnormal monitoring boiler data is combined with the number of abnormal operation and maintenance of the boiler to determine the construction and management method of the boiler pipeline model.

10. A computer system, comprising: A memory and processor connected by communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes a boiler pipe model construction and management method for vibration suppression processing as described in any one of claims 1-9.

Images