CN-122014537-A - Fan blade clearance monitoring method and system

CN122014537ACN 122014537 ACN122014537 ACN 122014537ACN-122014537-A

Abstract

The invention belongs to the technical field of fan operation and maintenance, and particularly discloses a method and a system for monitoring the clearance of a fan blade. The invention can overcome the defects of poor adaptability to the extreme environment, early warning lag, low data utilization rate, insufficient suitability and high operation and maintenance cost of the existing fan blade clearance monitoring product, can remarkably improve the adaptability of the fan blade clearance monitoring system to the extreme environment and the monitoring stability under the extreme environment, realizes the dynamic risk pre-judgment, avoids the problem of early warning lag, and has the advantages of high system multisource data fusion efficiency, high monitoring precision, strong suitability, low operation and maintenance cost, convenient formation of closed-loop operation and maintenance management, improvement of the operation efficiency of the fan and guarantee of safe operation of the fan.

Inventors

WANG JIAN
TANG HUI
Dong Wuxing

Assignees

成都鼎峰汇智科技有限公司

Dates

Publication Date: 20260512
Application Date: 20260408

Claims (10)

1. A method for monitoring fan blade clearance, comprising: Collecting a multi-dimensional monitoring data set of a target fan, real-time wind field data and predicted wind field data of a wind field where the target fan is located, wherein the multi-dimensional monitoring data set comprises initial blade clearance data, blade tip polarized light image data, real-time environment data, blade attitude data and tower deformation data; Carrying out data preprocessing on the multi-dimensional monitoring data set to obtain a preprocessed multi-dimensional monitoring data set; carrying out multi-source data fusion processing on the preprocessed multi-dimensional monitoring data set to obtain a fusion blade clearance distance; inputting the fusion blade clearance distance, the real-time wind field data and the predicted wind field data into a pre-trained clearance dynamic coupling model to perform clearance prediction, so as to obtain blade clearance distance change trend data of the target fan in a future time period; and extracting the predicted blade clearance distance of each future time point from the blade clearance distance change trend data, carrying out grading early warning judgment on the predicted blade clearance distance of each future time point, and outputting corresponding grading early warning information to a fan main control system and an operation and maintenance management platform of the target fan when the corresponding predicted blade clearance distance meets the set grading early warning condition.
2. The method for monitoring the clearance of a fan blade according to claim 1, wherein the step of performing data preprocessing on the multi-dimensional monitoring dataset to obtain a preprocessed multi-dimensional monitoring dataset comprises the steps of: and carrying out synchronous alignment, data noise reduction and outlier rejection on the multi-dimensional monitoring data set to obtain a preprocessed multi-dimensional monitoring data set.
3. The method for monitoring the clearance of a fan blade according to claim 1, wherein the performing multi-source data fusion processing on the preprocessed multi-dimensional monitoring data set to obtain a fused blade clearance distance comprises: Dynamically adjusting the weight of the initial blade clearance data and the blade tip polarized light image data by adopting a self-adaptive weighted fusion algorithm based on the real-time environment data, and carrying out weighted fusion on the initial blade clearance data and the blade tip polarized light image data to obtain a real-time fusion clearance distance; and correcting the real-time fusion clearance distance by using the blade attitude data and the tower barrel-shaped data to obtain the fusion blade clearance distance.
4. The fan blade clearance monitoring method according to claim 3, wherein when the weights of the initial blade clearance data and the blade tip polarized light image data are dynamically adjusted by adopting an adaptive weighted fusion algorithm based on real-time environment data, the weight adjustment rule of the adaptive weighted fusion algorithm is that the weight of the initial blade clearance data accounts for 30% -40% when the real-time environment data is in a set normal environment data range, the weight of the blade tip polarized light image data accounts for 60% -70%, and the weight of the initial blade clearance data accounts for 80% -90% when the real-time environment data is in a set severe environment data range, and the weight of the blade tip polarized light image data accounts for 10% -20%.
5. A method for monitoring clearance of a fan blade according to claim 3, wherein the correcting the real-time fusion clearance distance by using blade attitude data and tower cylinder data to obtain the fusion blade clearance distance comprises: determining a blade swing angle variable based on the blade attitude data, determining a blade swing clearance correction amount according to the blade swing angle variable, and correcting the real-time fusion clearance distance by using the blade swing clearance correction amount to obtain an initial correction clearance distance; and determining a tower cylinder clearance change correction amount according to the tower cylinder data, and correcting the initial correction clearance distance by utilizing the tower cylinder clearance change correction amount to obtain the fusion blade clearance distance.
6. The method for monitoring the clearance of a fan blade according to claim 1, wherein the step of performing step-by-step early warning judgment on the predicted clearance distance of the fan blade at each future time point, and outputting corresponding step-by-step early warning information to a fan main control system and an operation and maintenance management platform of a target fan when the corresponding predicted clearance distance of the fan blade meets a set step-by-step early warning condition comprises the steps of: the method comprises the steps of comparing predicted blade clearance distances of all future time points with set hierarchical early warning rules, outputting corresponding three-level early warning information to a fan main control system and an operation and maintenance management platform of a target fan when the corresponding predicted blade clearance distance is in a set three-level early warning distance interval, outputting corresponding two-level early warning information to the fan main control system and the operation and maintenance management platform of the target fan when the corresponding predicted blade clearance distance is in a set two-level early warning distance interval, and outputting corresponding one-level early warning information to the fan main control system and the operation and maintenance management platform of the target fan when the corresponding predicted blade clearance distance is in a set one-level early warning distance interval.
7. A method of fan blade clearance monitoring according to claim 1, further comprising: And uploading the multidimensional monitoring data set, the real-time wind field data, the predicted wind field data, the fusion blade clearance distance and the blade clearance distance change trend data to a cloud database for storage.
8. The fan blade clearance monitoring system is characterized by comprising a composite sensing module, an attitude sensing module, a deformation detection module, a data processing module and a linkage control module; the composite sensing module is arranged on a tower of a target fan and comprises a millimeter wave radar, a polarized light camera and an environment sensing unit, wherein the millimeter wave radar is used for collecting initial blade clearance data of the target fan, the polarized light camera is used for collecting blade tip polarized light image data of the target fan, the environment sensing unit is used for collecting real-time environment data of the target fan, the attitude sensing module is arranged at the root of the blade of the target fan and comprises an IMU inertial measurement unit and is used for collecting blade attitude data of the target fan, the deformation detection module is arranged on the side wall of the tower of the target fan and comprises a distributed strain sensor and is used for collecting tower barrel deformation data of the target fan, the data processing module is used for collecting initial blade clearance data, blade tip polarized light image data, real-time environment data, blade attitude data and tower barrel-shaped variable data to form a multi-dimensional monitoring data set of the target fan, data preprocessing is carried out on the multi-dimensional monitoring data set to obtain a preprocessed multi-dimensional monitoring data set, multi-source data fusion processing is carried out on the preprocessed multi-dimensional monitoring data set to obtain a fusion distance, the blade clearance distance is used for predicting trend data of the blade clearance distance of the target fan at a future time, the predicted trend data of the future time is input into a future wind field clearance distance prediction model, the trend data of the blade clearance distance is predicted, and the trend data is changed from the future wind clearance data of the future distance of the wind field is predicted, and the linkage control module establishes communication connection with a fan main control system and an operation and maintenance management platform of the target fan and is used for transmitting the grading early warning information to the fan main control system and the operation and maintenance management platform of the target fan.
9. The fan blade clearance monitoring system of claim 8, further comprising a data operation and maintenance module and a power supply module, wherein the data operation and maintenance module is used for uploading a multi-dimensional monitoring data set, real-time wind field data, predicted wind field data, fusion blade clearance distance, blade clearance distance change trend data and grading early warning information to a cloud database for storage, and the power supply module is used for supplying power to the composite sensing module, the attitude sensing module, the deformation detection module, the data processing module, the linkage control module and the data operation and maintenance module.
10. A fan blade clearance monitoring system, comprising: a memory for storing instructions; and the processor is used for reading the instructions stored in the memory and executing the fan blade clearance monitoring method according to the instructions.

Description

Fan blade clearance monitoring method and system Technical Field The invention belongs to the technical field of fan operation and maintenance, and particularly relates to a fan blade clearance monitoring method and system. Background The fan blade clearance monitoring is a core link for guaranteeing safe and stable operation of the wind generating set, and aims to accurately monitor the minimum distance between the blade and the tower in real time, timely early warn collision risk and avoid occurrence of 'tower sweeping' accidents, so that economic losses caused by damage of the fan blade, damage of the tower and shutdown are reduced. At present, a certain application scale is formed by a fan blade clearance monitoring technology and a product, but the existing fan blade clearance monitoring product still has the following defects in the actual application process: 1. Poor adaptability to severe environments and unstable monitoring precision, the existing fan blade clearance monitoring products rely on laser radars or vision cameras for ranging, are easy to be shielded, interfered by signal reflection or corroded under severe environments such as sand dust, rain and snow, strong wind, high salt mist and the like, cause increase of measurement errors, even have the conditions of data loss, false alarm or missing report, and are low in monitoring reliability. 2. The method is lack of dynamic risk pre-judging capability, and early warning lag is that the prior art mainly focuses on 'real-time ranging', can only trigger early warning when the clearance distance is close to a safety threshold, and cannot pre-judge the clearance risk in short time in the future based on dynamic factors such as blade swing, tower deformation, wind field change and the like. This hysteresis often results in the control system or service personnel not being able to adjust the fan operating conditions, thereby causing an accident. 3. The multi-sensor fusion effect is poor, the data utilization rate is low, although a part of existing products try to adopt multi-sensor combination, most of the existing products are simple data superposition application, an effective data fusion mechanism is lacked, and the weight of the sensing data cannot be dynamically adjusted according to environmental changes, so that the accuracy and the continuity of the monitoring data are difficult to be considered. 4. The system has poor adaptability and high operation and maintenance cost, the existing monitoring system is mostly designed in a fixed specification, is difficult to flexibly adapt to fans of different types, is complex to install and debug, and part of core sensors depend on import, so that the overall cost is high, and the large-scale popularization and application are limited. 5. The data linkage is insufficient, and the cooperative operation and maintenance decision cannot be made, namely, the clearance monitoring data are stored independently and are not effectively linked with the fan main control system and the operation and maintenance management platform. The monitoring system can only realize a single early warning function, cannot combine the clearance monitoring data with links such as pitch control, shutdown protection, operation and maintenance scheduling and the like, cannot form effective closed-loop management, and cannot fully exert the value of the clearance monitoring data. ‌ ‌ A Disclosure of Invention The invention aims to provide a fan blade clearance monitoring method and system, which are used for solving the problems in the prior art. In order to achieve the above purpose, the present invention adopts the following technical scheme: In a first aspect, a method for monitoring clearance of a fan blade is provided, including: Collecting a multi-dimensional monitoring data set of a target fan, real-time wind field data and predicted wind field data of a wind field where the target fan is located, wherein the multi-dimensional monitoring data set comprises initial blade clearance data, blade tip polarized light image data, real-time environment data, blade attitude data and tower deformation data; Carrying out data preprocessing on the multi-dimensional monitoring data set to obtain a preprocessed multi-dimensional monitoring data set; carrying out multi-source data fusion processing on the preprocessed multi-dimensional monitoring data set to obtain a fusion blade clearance distance; inputting the fusion blade clearance distance, the real-time wind field data and the predicted wind field data into a pre-trained clearance dynamic coupling model to perform clearance prediction, so as to obtain blade clearance distance change trend data of the target fan in a future time period; and extracting the predicted blade clearance distance of each future time point from the blade clearance distance change trend data, carrying out grading early warning judgment on the predicted blade clearance distance of each future time point, and