CN119250488A

CN119250488A - An intelligent operation and maintenance management method for energy technology based on low-altitude areas

Info

Publication number: CN119250488A
Application number: CN202411768947.7A
Authority: CN
Inventors: 陈铿锋; 陈锐文; 陈嘉炜; 许谦政; 李成; 黄德全
Original assignee: Guangdong Xinyi Information Technology Co ltd
Current assignee: Guangdong Xinyi Information Technology Co ltd
Priority date: 2024-12-04
Filing date: 2024-12-04
Publication date: 2025-01-03
Anticipated expiration: 2044-12-04
Also published as: CN119250488B

Abstract

The present invention discloses an intelligent operation and maintenance management method for energy technology based on the low-altitude field, which relates to the field of energy technology operation and maintenance technology, and specifically includes the following steps: analyzing the acquired operating status information of each area of the fan blade, and generating the turbulence stress intensity coefficient and the instantaneous load impact coefficient of each area respectively; constructing a turbulence impact assessment model for the generated turbulence stress intensity coefficient and the instantaneous load impact coefficient of each area, generating the load impact coefficient of each area, and analyzing it after generation, assessing the instantaneous load impact degree of turbulence on the fan blade, and dividing it into three categories of low load impact, medium load impact and high load impact according to the assessment results; taking corresponding measures according to the division results. The present invention solves the assessment problem of the instantaneous load impact of turbulence on the fan blade, and realizes the real-time optimization of the fan operation and safe and efficient operation.

Description

Intelligent operation and maintenance management method for energy technology based on low-altitude field

Technical Field

The invention relates to the technical field of operation and maintenance of energy technology, in particular to an intelligent operation and maintenance management method of energy technology based on the low-altitude field.

Background

The energy technology refers to a scientific technology and an engineering method related to the development, utilization, transmission and management of surrounding energy, and is a key field for guaranteeing energy supply, improving energy utilization efficiency and promoting green development in the modern society. The purpose of carrying out operation and maintenance management on the energy technology is to ensure the efficient, safe and stable operation of the energy system, prolong the service life of equipment, reduce the operation and maintenance cost and reduce the resource waste through an intelligent means, thereby playing the economic and environmental benefits of the energy technology to the maximum extent. The energy technology in the low-altitude field, such as low-altitude wind power generation and solar facilities, is influenced by factors such as environmental complexity, weather variability, operating condition specificity and the like, and the traditional operation and maintenance mode is difficult to meet the high-efficiency management requirement, so that the low-altitude energy facilities are monitored and optimized in real time by the intelligent operation and maintenance management method, the stability of energy supply can be ensured, the dynamic change in the low-altitude environment can be effectively realized, and the overall operation and maintenance efficiency and facility reliability are improved.

The existing intelligent operation and maintenance management technology based on the energy technology in the low-altitude field mainly realizes operation and maintenance management of energy facilities through a sensor network, a real-time data acquisition and a remote monitoring platform. Specifically, sensors are arranged on facilities such as low-altitude wind power generation and solar power generation and are used for monitoring key information such as equipment operation states, environmental conditions (such as wind speed, temperature, humidity and the like) and output power, and the data are transmitted to an operation and maintenance platform through a wireless communication network. The operation and maintenance platform displays and records the acquired data in real time, and operation and maintenance personnel can check the operation condition of the equipment through a visual interface and identify and locate abnormal problems such as equipment faults, abnormal power output or overlarge environmental influence according to preset alarm rules. Upon detecting a problem, the platform may automatically generate a maintenance notification or process the problem by scheduling a function orchestrated operation staff. In addition, some technologies have introduced historical data comparison and trend analysis for predicting potential problems and providing preventive maintenance recommendations, thereby improving operational efficiency and reducing unplanned downtime of energy facilities.

The prior art has the following defects:

In low altitude wind power plant operation, when turbulence phenomenon occurs in the windward area in front of the wind turbine due to complex terrain (such as valleys or steep slopes) or wake effects of adjacent wind turbine arrays, the data acquired by the wind speed sensor at different heights will be significantly different due to temporal and spatial non-uniformity of turbulence. This turbulence phenomenon can cause major transient load impacts to the fan blades, while being transferred to the tower through the blades, possibly inducing additional vibration of the tower. However, the prior art generally only analyzes data of a single sensor independently, lacks joint resolution capability for multi-sensor data, and thus has difficulty in scientifically evaluating instantaneous load impact of turbulence on fan blades. The limitation can cause underestimation or misjudgment of turbulence influence, so that the fan cannot take deceleration or stopping measures in time under load impact, further the mechanical stress accumulation of the blades is increased, the fatigue damage and the failure risk of key parts are caused, the maintenance cost is obviously improved, and the operation safety and the operation efficiency of the fan are influenced.

The above information disclosed in the background section is only for enhancement of understanding of the background of the disclosure and therefore it may include information that does not form the prior art that is already known to a person of ordinary skill in the art.

Disclosure of Invention

The invention aims to provide an intelligent operation and maintenance management method for energy technology based on the low-altitude field, so as to solve the problems in the background technology.

In order to achieve the purpose, the invention provides the following technical scheme that the intelligent operation and maintenance management method for the energy technology based on the low-altitude field specifically comprises the following steps:

In the operation of a low-altitude wind power generation facility, monitoring wind speed information of a windward area in the front of a fan in real time, detecting whether a turbulence phenomenon occurs, and acquiring operation state information of each area of the fan blade through a sensor network deployed on the fan blade when the turbulence phenomenon is detected;

Analyzing the acquired running state information of each area of the fan blade, and respectively generating a turbulence stress intensity coefficient and an instantaneous load impact coefficient of each area;

a turbulence impact evaluation model is constructed for the generated turbulence stress intensity coefficient and the instantaneous load impact coefficient of each area, the load impact coefficient of each area is generated, analysis is carried out after the generation, the instantaneous load impact degree of the turbulence on the fan blade is evaluated, and the three types of low load impact, medium load impact and high load impact are classified according to the evaluation result;

According to the dividing result, corresponding measures are respectively adopted for the fan blades under the conditions of low load impact, medium load impact and high load impact;

The operation state and turbulence influence of the fan blades are continuously monitored, a turbulence influence evaluation model and a fan scheduling strategy are dynamically adjusted according to real-time monitoring data, the operation state of the fan is optimized, and the safety and the operation efficiency of the fan are improved.

Preferably, the obtained operation state information of each area of the fan blade is analyzed to respectively generate a turbulent flow stress intensity coefficient and an instantaneous load impact coefficient of each area, and the method specifically comprises the following steps:

preprocessing the acquired running state information of each area of the fan blade;

extracting wind speed gradient information and vibration response information in the operation state information of each area of the preprocessed fan blade;

And analyzing the extracted wind speed gradient information and vibration response information to respectively generate turbulence stress intensity coefficients and instantaneous load impact coefficients of all areas.

Preferably, the logic for obtaining the turbulent stress intensity coefficient of each region is as follows:

Extracting wind speed gradient information in the operation state information of each area of the preprocessed fan blade, wherein the wind speed gradient information comprises average wind speed, blade vibration acceleration and air pressure fluctuation amplitude of the blade surface of each area at different time periods in a period of time, and respectively using functions according to time sequences 、AndThe representation is made in such a way that,As a point of time in time it is,Indicating that within a period of timeTime of day (time)The average wind speed of the individual zones is,Indicating that within a period of timeTime of day (time)The blade vibration acceleration of the individual zones,Indicating that within a period of timeTime of day (time)The air pressure fluctuation amplitude of the blade surface of each area is defined as the time period,,Is a positive integer;

the turbulence stress intensity coefficient of each area is calculated, and a specific calculation formula is as follows:

;

in the formula, Is the firstTurbulent stress intensity coefficient of individual regions.

Preferably, the logic for obtaining the instantaneous load impact coefficient of each region is as follows:

extracting vibration response information in the operation state information of each area of the preprocessed fan blade, wherein the vibration response information comprises the blade curvature, the blade surface stress variation amplitude and the blade vibration frequency of each area at different time periods in a period of time, and respectively using functions according to time sequences 、AndThe representation is made in such a way that,As a point of time in time it is,Indicating that within a period of timeTime of day (time)The curvature of the vane in the individual regions,Indicating that within a period of timeTime of day (time)The magnitude of the change in blade surface force in each region,Indicating that within a period of timeTime of day (time)Blade vibration frequencies of individual regions, defined as time periods,,Is a positive integer;

the instantaneous load impact coefficient of each area is calculated, and a specific calculation formula is as follows:

;

in the formula, Is the firstInstantaneous load impact coefficient of each zone.

Preferably, a turbulence influence evaluation model is constructed for the generated turbulence stress intensity coefficient and instantaneous load impact coefficient of each region, and the load impact coefficient of each region is generated, specifically comprising the following steps:

Collecting turbulence stress intensity coefficient, instantaneous load impact coefficient and corresponding load impact coefficient of a plurality of areas generated in the past period of time and calibrating the turbulence stress intensity coefficient, the instantaneous load impact coefficient and the corresponding load impact coefficient as follows 、And,A number representing the turbulence stress intensity coefficient, instantaneous load impact coefficient and corresponding load impact coefficient for several individual zones generated over a period of time,,Is a positive integer and forms a historical dataset from the collected data over a period of time;

Selecting a multiple regression model as a turbulence influence evaluation model, training through a historical data set, determining the value of a regression coefficient, and according to the formula:

;

in the formula, 、AndIs a regression coefficient;

Optimizing regression coefficients by minimizing errors between predicted and actual values, and finally determining regression coefficients 、AndIs a value of (2);

inputting turbulence stress intensity coefficients of each region generated in real time to a constructed turbulence influence evaluation model by using the finally determined regression coefficients And transient load impact coefficientGenerating load impact coefficients of all areas in real time。

Preferably, the load impact coefficients for the respective regions generatedAnalysis is performed to generate impact assessment indexAccording to the formula: and the generated impact evaluation index With a preset impact evaluation index threshold intervalThe instantaneous load impact degree of turbulence on the fan blade is evaluated according to the comparison result, and the instantaneous load impact degree is divided into three types of low load impact, medium load impact and high load impact according to the evaluation result, wherein the specific comparison analysis and division are as follows:

If it is The instantaneous load impact degree of the turbulence on the fan blade is low, and the fan blade is divided into low load impact;

If it is The instantaneous load impact degree of the turbulence on the fan blade is the medium range degree, and the medium load impact is divided;

If it is The turbulence divides the instantaneous load impact of the fan blade into high load impacts if it is high.

Preferably, according to the division result, corresponding measures are respectively taken for the fan blades under the conditions of low load impact, medium load impact and high load impact, specifically:

For the fan blade with the low load impact as the dividing result, the current running state of the fan blade is maintained, the fan blade is ensured to run in a safe load range, and the load condition of the fan blade is monitored in real time so as to ensure the stability of the fan blade;

for the fan blade under the condition of medium load impact as a dividing result, the method adopts the steps of adjusting the operation parameters of the fan, reducing load fluctuation, optimizing the load distribution of the blade and continuously monitoring the operation state of the blade;

For the fan blade with the high load impact as the dividing result, the measures are taken to immediately start the protection mechanism, quickly reduce the rotating speed of the fan, avoid the blade bearing impact force, automatically schedule and improve the steady-state support of the fan tower through the system, share the load pressure of the blade, and simultaneously monitor the vibration and stress data of the fan blade in real time and early warn the abnormal situation.

In the technical scheme, the invention has the technical effects and advantages that:

1. according to the invention, through deployment of the multi-sensor network and real-time data acquisition, the limitation of independent analysis of a single sensor in the prior art is overcome, and the comprehensive monitoring of the running states of different areas of the fan blade is realized. The high-precision quantitative data such as the curvature, the stress variation amplitude and the vibration frequency of the blade are obtained, and the turbulent flow stress intensity coefficient and the instantaneous load impact coefficient are generated by combining a complex mathematical calculation formula, so that the non-uniform characteristics of the turbulent flow in time and space are effectively captured, and the evaluation process is more accurate and comprehensive. The multi-parameter joint analysis method significantly improves the scientificity and reliability of turbulence influence assessment.

2. According to the method, the quantitative evaluation of the instantaneous load impact degree of the turbulence on the fan blade is realized by constructing the turbulence impact evaluation model and generating the load impact coefficient. The introduction of the multiple regression model not only enables the full utilization of the historical data to be possible, but also ensures the adaptability and accuracy of the model to real-time turbulence conditions by dynamically adjusting regression coefficients. In addition, through the calculation of the impact evaluation index and the comparison with a preset threshold interval, the classification and quantization treatment of the turbulence influence are further refined, and a scientific basis is provided for the running state division of the fan blade. The classification mode based on quantitative analysis can help the fan to take corresponding measures under different load impact conditions, so that the operation safety is ensured, and the waste of resources is avoided.

3. The invention fully embodies the practicability and the intellectualization of the invention by adopting the protection and the scheduling measures under the conditions of low, medium and high load impact. The invention realizes the balance of the running efficiency and the safety of the fan by keeping the normal running under the condition of low load impact, optimizing the running parameters under the condition of medium load impact and protecting the emergency under the condition of high load impact. Meanwhile, due to the introduction of a continuous monitoring and dynamic adjusting mechanism, the system can optimize the turbulence influence evaluation model and the scheduling strategy in real time, and the instantaneity and the accuracy of an evaluation result are ensured. The closed-loop type dynamic scheduling and evaluation design can effectively reduce the mechanical stress accumulation of the blades and the tower, prolong the service life of equipment, remarkably improve the overall operation efficiency of the fan, reduce the maintenance cost and have stronger industrial application value and market competitiveness.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings for those skilled in the art.

Fig. 1 is a schematic flow chart of an intelligent operation and maintenance management method of energy technology based on the low-altitude field.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments may be embodied in many different forms and should not be construed as limited to the examples set forth herein, but rather, the example embodiments are provided so that this disclosure will be more thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.

The invention provides an intelligent operation and maintenance management method of energy technology based on the low-altitude field as shown in figure 1, which specifically comprises the following steps:

In order to monitor the wind speed information of the windward area in front of the fan in real time and detect whether turbulence occurs, a plurality of wind speed sensors can be arranged in front of the fan and are arranged at different heights so as to ensure the comprehensive monitoring of wind fields. The data of the sensor can be transmitted to a central data processing system in real time, and the system can analyze the fluctuation condition of the wind speed through the real-time acquisition of the wind speed data. Turbulence phenomena typically result in severe fluctuations or non-uniformities in wind speed, and software can identify anomalies in changes in wind speed by analyzing the amplitude and frequency of these fluctuations. When the change of the wind speed exceeds a set threshold value, the system automatically judges the turbulence phenomenon and gives an alarm. The process relies on real-time data of the wind speed sensor and an analysis algorithm, so that the fan can respond timely, and negative effects caused by turbulence are avoided.

After the turbulence phenomenon is detected, the system further analyzes the influence of the turbulence on the fan according to the running state information of the fan blade. This is accomplished by sensors deployed in different areas of the fan blade, including vibration sensors, temperature sensors, pressure sensors, etc., distributed at the root, middle and tip of the blade. By means of real-time data acquisition of the sensors, the system can monitor various influences of turbulence on the fan blade, such as increased vibration and temperature fluctuation. By combining wind speed information and blade state information, software can acquire load impact conditions of different blade areas under the influence of turbulence, so that detailed basis is provided for subsequent evaluation and fan adjustment. The high precision and the real-time performance of the data acquisition can effectively reflect the instantaneous load borne by the blade, so that the fan can make corresponding adjustment.

In order to accurately acquire the running state information of each area of the fan blade, a sensor network deployed on the blade plays a key role. The sensors need to be optimally configured according to the load characteristics of different areas, for example, the sensors at the root of the blade can mainly monitor vibration and temperature change, and the blade tip part mainly monitors the airflow characteristics such as wind speed, pressure and the like. The sensor transmits the acquired data to the data acquisition system in real time through the wireless communication module, and the data acquisition system performs preliminary processing and pre-analysis on the real-time data so as to facilitate subsequent further detailed analysis. In this way, the load changes of different areas of the fan blade under the action of turbulence can be captured and fed back in real time, and the software can automatically analyze and generate relevant load evaluation parameters. The real-time processing and analysis capability of the data ensures a fast response of the system to the effects of turbulence, thereby enabling the load condition of the blade to be assessed in a first time.

This series of measures is intended to solve the problem of insufficient assessment of turbulence phenomena in the prior art. The conventional technology often relies on joint analysis of single sensor or neglect of multi-sensor data, so that the influence of turbulence on the fan blade is difficult to accurately evaluate, and necessary protection measures cannot be timely made. Wind speed fluctuation and load impact caused by turbulence are different in different fan blade areas, and the non-uniformity makes the traditional method incapable of comprehensively capturing the influence of turbulence, so that the fan cannot be decelerated or stopped in time, the mechanical stress of the blades and the tower barrel is increased, and further the risks of fatigue damage and faults are increased. Through the multi-sensor network and the real-time data analysis in the technical scheme, the instantaneous load impact of turbulence on blades in different areas can be accurately estimated, a more scientific scheduling basis is provided for the fan, potential damage caused by the turbulence is reduced, the safety and the operation efficiency of the fan are improved, and the maintenance cost is effectively reduced.

In this embodiment, the acquired operation state information of each area of the fan blade is analyzed, and a turbulent stress intensity coefficient and an instantaneous load impact coefficient of each area are respectively generated, which specifically includes the following steps:

Preprocessing the acquired running state information of each area of the fan blade is a key step for ensuring the data analysis precision and the reliability of the generated parameters, because the original data may be affected by factors such as sensor faults, environmental interference or network delay, and the like, and the problems of abnormal values, noise, missing data or inconsistent formats exist. The preprocessing specifically comprises the following steps of firstly cleaning data, removing abnormal values and error data by using a statistical distribution method (such as 3 sigma rule) or a trend analysis algorithm, secondly, complementing the missing data by using an interpolation method (such as linear interpolation or spline interpolation) to ensure the continuity of the data, then eliminating high-frequency noise interference in the data by using a denoising algorithm such as low-pass filtering or Kalman filtering and the like, retaining key characteristics, finally, carrying out format unification and time synchronization on the data, ensuring that the data acquired by each sensor has consistent time stamps and units, and mapping the values to a unified range (such as between 0 and 1) by normalization processing to eliminate the magnitude difference of the data with different dimensions. The preprocessing operation is automatically executed through software, so that the integrity and quality of data can be remarkably improved, a reliable basis is provided for the subsequent calculation of the turbulence stress intensity coefficient and the instantaneous load impact coefficient, and the accuracy and the scientificity of an evaluation result are ensured.

Extracting wind speed gradient information and vibration response information in the operation state information of each area of the preprocessed fan blade, wherein the wind speed gradient information is used for representing turbulence intensity, and the vibration response information is used for representing instantaneous load impact;

In this embodiment, the logic for obtaining the turbulence stress intensity coefficient of each region is as follows:

In order to extract wind speed gradient information, blade vibration acceleration and air pressure fluctuation amplitude in the operation state information of each area of the preprocessed fan blade, data needs to be acquired in real time through a sensor network deployed on the fan blade. These sensors typically include a wind speed sensor, an acceleration sensor, and a pressure sensor, which are mounted on different blade areas (e.g., root, middle, and tip of the blade). Through the sensor network, wind speed changes, vibration responses of the blades and air pressure fluctuation data in the areas can be continuously recorded. By means of a data acquisition system, these data can be collected periodically and stored in a database, and then pre-processed using data processing software, such as denoising, interpolation, time synchronization, etc., to ensure accuracy and consistency of the data. Next, time-series data of the average wind speed, vibration acceleration, and air pressure fluctuation in each region are extracted using a statistical method and a signal processing algorithm (such as a moving average, fourier transform, etc.). These data will serve as the basis for subsequent analysis to provide the necessary inputs for calculating the turbulence stress intensity coefficient.

Regarding the acquisition and interpretation of these three types of quantitative data, wind speed data is typically acquired by wind speed sensors that, by measuring the wind speed change in the frontal windward region of the wind turbine, combine the accuracy of its installation and the sampling frequency to generate an accurate wind speed record. The vibration acceleration of the blade is measured by acceleration sensors, the sensors can capture the tiny vibration of the fan blade under different wind speeds and turbulent environments, and the dynamic response of the blade when the blade is impacted by the turbulence can be deduced by the acceleration value. The air pressure fluctuation amplitude is collected by the pressure sensor arranged on the surface of the blade, and can capture the air pressure change of the air flow flowing on the surface of the blade, and the change can reflect the influence of the turbulence intensity on the blade. The sensors generate time sequences according to the acquired data at specific time intervals, and then data processing methods such as average value calculation and standardization can be utilized to extract indexes such as wind speed, vibration acceleration, air pressure fluctuation amplitude and the like of each area and analyze the indexes so as to further calculate turbulence stress intensity coefficients. The acquisition and processing of the data can provide necessary basis for real-time evaluation of the stress state of the fan blade.

;

The design of the calculation formula is to accurately evaluate the stress intensity of the turbulence on the fan blade and consider the influence of the turbulence on different areas of the blade. First, the second derivative is calculated to capture the acceleration of the wind speed change, reflecting the severity of the turbulence. Turbulence is essentially a highly unstable phenomenon in the airflow, the speed of which varies not only over the instantaneous wind speed, but also over the rate of change of wind speed. By calculating the acceleration of the wind speed through the second derivative, the dynamic characteristic of the turbulence can be obtained, so that the stress generated by the turbulence on the surface of the blade can be captured better. Next, the purpose of using a fourth-order operation is to amplify the effect of turbulence intensity on the blade, since turbulence-generated pressure fluctuations are highly nonlinear, and increases in turbulence intensity typically result in an exponential increase in stress. The fourth-order operation can effectively emphasize the nonlinear effect of turbulence intensity on the blade surface. The third power is used for quantifying the influence of vibration acceleration, the vibration acceleration is the structural reaction of the blade under the action of air flow, and the third power operation can amplify the mechanical stress born by the blade, so that the load influence of the blade can be estimated more accurately. The multiplication of the wind speed gradient, the vibration acceleration and the pressure fluctuation information takes the combined action of the factors at the same time point into consideration, and the turbulence, the vibration of the blade and the pressure fluctuation act on the surface of the blade together to directly influence the instantaneous load impact of the blade. Finally, the use of a constant integral is to accumulate these transient effects over a period of time, and the integral calculation can combine the effects at different time points to obtain a comprehensive turbulence stress intensity assessment, taking into account that turbulence is a time-varying phenomenon. In general, the calculation formula can evaluate the stress intensity of the fan blade under the turbulent flow condition more accurately by comprehensively considering the turbulent flow, vibration and air pressure fluctuation and combining the high-order nonlinear operation and integral processing.

First, theTurbulent stress intensity coefficient of individual regionsThe magnitude of the (b) directly reflects the strength of the area affected by the turbulence, so that the instantaneous load impact degree of the fan blade is affected, and the larger the coefficient is, the stronger the turbulence stress of the area is, and the larger the load impact of the blade is. Specifically, the turbulence stress intensity coefficient is calculated by combining factors such as wind speed gradient, vibration acceleration, air pressure fluctuation and the like, and the nonlinear influence of turbulence can be effectively quantified. When the turbulence stress intensity coefficient is larger, the turbulence effect of the area is stronger, the load change of the fan blade in the area is more severe, and the mechanical stress is also obviously increased, so that the fan blade faces higher load impact risk. Therefore, by calculating the turbulence stress intensity coefficient, the instantaneous load impact degree of different areas can be accurately estimated, and corresponding scheduling or protecting measures are adopted to prevent fatigue damage or faults of the fan blade caused by excessive instantaneous load.

In this embodiment, the logic for obtaining the instantaneous load impact coefficients of each region is as follows:

To extract vibration response information in the operation state information of each area of the preprocessed fan blade, a data acquisition method of a sensor network can be adopted. First, a plurality of high-precision sensors, such as acceleration sensors, strain gauges and displacement sensors, are mounted on the fan blade, and these sensors can monitor vibration, bending and stress conditions of the blade in real time during the operation of the fan. The sensor transmits data to the central control system through a wireless network, and the system cleans noise and irrelevant information through a data preprocessing and filtering algorithm to ensure the accuracy of the data. Aiming at the characteristics of the curvature, the stress variation amplitude, the vibration frequency and the like of the blade, the frequency domain analysis can be carried out on the original data by utilizing signal processing technologies such as Fourier transform and the like, and detailed vibration response data of different areas at different moments can be extracted, so that the real-time running state of each area of the fan blade can be obtained.

For quantitative data of three types, namely the curvature of the blade, the stress variation amplitude of the surface of the blade and the vibration frequency of the blade, at different moments in time, the acquisition process of the quantitative data involves the cooperation of a plurality of sensors. The bending of the blade may be obtained by means of strain sensors mounted on the surface of the blade, which sensors are able to measure the degree of bending of the blade under the influence of wind. The strain sensor records the deformation of the blade at each point, and the bending degree of the blade can be calculated according to the data. The deformation and stress change of the blade under the action of wind force are measured by the strain gauge and the force sensor according to the amplitude of the stress change of the blade surface. According to the data fed back by the sensor, the stress change condition of the blade at different time points can be calculated. Finally, the vibration frequency of the blade can be obtained by capturing vibration signals of the fan blade in each area through an acceleration sensor and combining a frequency analysis method (such as fast Fourier transform). Through extraction and analysis of the data, the running state of the fan blade can be comprehensively known, and key parameters are provided for subsequent turbulence influence evaluation.

;

in the formula, Is the firstInstantaneous load impact coefficient of each zone.

The calculation formula of the instantaneous load impact coefficient adopts a fixed integral form, mainly because the load impact suffered by the fan blade in the running process is instantaneous and frequently changes, and the change not only depends on a time factor, but also is closely related to the specific area position, wind speed fluctuation and turbulence characteristics of the fan blade. By integrating the data of stress, bending, vibration frequency and the like of the blade in different areas, the dynamic change of load impact can be accurately captured in time and space. Firstly, three types of quantitative data, namely the curvature of the blade, the stress variation amplitude of the surface of the blade and the vibration frequency of the blade, are defined in the calculation process, and each type of data is acquired in real time through a sensor network and converted into a quantifiable digital signal. Then, by expressing these data in the form of a function, the blade stress and vibration states of different areas at different moments can be reflected. For example, the curvature of the blade can be represented by a strain value measured by a strain sensor, the variation amplitude of the stress of the blade is calculated by a force signal measured by a force sensor, and the vibration frequency is obtained by frequency domain analysis of vibration data acquired by an acceleration sensor. These three types of data represent different response characteristics of the blade under the influence of turbulence and wind velocity variations, respectively. The method is used for multiplying and integrating the three powers of the curvature of the blade, the stress variation amplitude of the surface of the blade and the four powers of the vibration frequency of the blade, so as to accurately capture the nonlinear influence of turbulence on the load impact of the fan blade. In actual operation, the curvature of the blade, the amplitude of the surface stress variations and the interaction of the vibration frequency and turbulence generally exhibit strong nonlinear characteristics, and the respective degree of influence is exacerbated with variations in wind speed and turbulence intensity. By doing the third and fourth power operations on these parameters, it is possible to amplify their effect on load impacts under extreme conditions, especially in strong winds and turbulence fluctuations, where the response of the blade is more intense and the exponential operation of the parameter values helps to simulate this process accurately. The three-power and four-power operation is used, acceleration effect of the parameters on load impact under high load condition can be emphasized, and accumulated calculation is carried out on blade states of all moments and areas through the fixed integral, so that the method is beneficial to comprehensively evaluating instantaneous load impact degree caused by turbulence, and finally scientific basis is provided for safety evaluation and scheduling decision of fan blades.

First, theInstantaneous load impact coefficient for individual zonesThe magnitude of (2) directly reflects the degree of load impact to which the region is subjected by turbulence. Specifically, the load impact coefficient is calculated by weighted summation and integration of the third power of the blade curvature, the third power of the surface stress variation amplitude and the fourth power of the blade vibration frequency, and the variation of the parameters can capture the transient fluctuation and nonlinear effect caused by turbulence with high sensitivity. When the load impact coefficient is larger, the effect of turbulence on the blades in the area is stronger, and the load impact is more severe, so that the influence of turbulence on the fan blades is more remarkable in the area. Conversely, a smaller load-impact coefficient indicates a lighter load impact in this region and less impact of turbulence on the instantaneous loading of the blade. Therefore, by comparing the load impact coefficients of different areas and combining the comparison of the evaluation coefficients and the preset threshold value, the instantaneous load impact degree of turbulence on the fan blade can be accurately evaluated, and whether scheduling or protection measures are needed to be adopted or not is judged, so that the safety and the operation efficiency of the fan are ensured.

in this embodiment, a turbulence impact evaluation model is constructed for the generated turbulence stress intensity coefficient and instantaneous load impact coefficient of each region, and the load impact coefficient of each region is generated, which specifically includes the following steps:

The collection of the turbulence stress intensity coefficients, instantaneous load impact coefficients, and corresponding load impact coefficients for each region generated over a period of time may be performed by a combination of a real-time monitoring system and a data storage system. Firstly, high-precision sensors are arranged in each area of the fan blade, and the sensors can acquire data such as wind speed, airflow pressure, blade surface stress, vibration and the like in real time. The raw data are preprocessed and transmitted to a central computing unit through a communication network. The data acquisition system is then used to combine the real-time sensor data with the historical data, and the turbulence stress intensity, load impact and other relevant data over a period of time are stored and calibrated periodically through a set data window. In order to ensure the accuracy and integrity of the data, the data acquisition period and transmission frequency can be set, such as batch storage of sensor data once per hour or minute. Through continuous collection and management of the data, a historical data set is formed, and a real-time analysis system is combined to extract turbulence stress intensity coefficients, instantaneous load impact coefficients and load impact coefficients of all areas. Eventually, these data will be stored in a cloud database or local database for use in subsequent model training and real-time computing. In addition, in order to ensure the validity of the data, a data quality detection mechanism can be introduced to monitor the integrity and accuracy of the data in real time, so that no abnormal data is ensured to influence the analysis result.

Will beThe positive integer of 3 or more is defined to ensure that a sufficient set of equations can be formed to accurately calculate the value of the regression coefficient when constructing the turbulence influence evaluation model. Since there is only one target equation and the number of regression coefficients to be calculated is three, at least three equations are needed to construct one system of equations, so that the calculation of the regression coefficients has a solution and the solution is unique. If there are fewer than three data points, there will be insufficient equations to support the training of the regression model, possibly resulting in over-fitting or inaccurate calculations, and an inability to effectively estimate the impact of turbulence on the fan blade load impact. Therefore, it is necessary to collect at least three data points, ensuring the sufficiency of the data set and the accuracy of the regression model. By the limitation, stable and reliable regression coefficient estimation can be provided in practical application, so that the reliability of an estimation result and the prediction capability of a system are improved.

;

in the formula, 、AndIs a regression coefficient;

The multiple regression model is a statistical analysis method for studying the relationship between multiple independent and dependent variables. In a multiple regression model, the dependent variable (i.e., the target variable) is predicted by a linear combination of a plurality of independent variables, each of which has a corresponding regression coefficient that represents the degree of influence of the independent variable on the dependent variable. The multiple regression model can process the interrelationship among a plurality of complex factors and is an effective tool for multi-factor analysis and prediction. In the technical scheme, a multiple regression model is selected as a turbulence influence evaluation model because two parameters, namely a turbulence stress intensity coefficient and an instantaneous load impact coefficient, are related to each other and affect the load impact of the fan blade together. Therefore, the multiple regression model is utilized to effectively relate the two parameters to the load impact coefficient of the target, and further evaluate the influence of turbulence on the fan blade. Through the historical data set training model, the optimal value of the regression coefficient can be determined by comparing the error between the actual load impact coefficient and the calculated value in the historical data, so that the model can accurately predict the future load impact condition in the actual application.

In this regression model, three regression coefficients、AndA constant term (typically representing a deviation or reference value), a turbulence stress intensity coefficient, and an instantaneous load impact coefficient, respectively.Typically a constant term, acts to adjust and correct model bias,Reflects the influence degree of the turbulent flow stress intensity coefficient on the load impact coefficient,Reflecting the impact of the transient load factor. The three regression coefficients are determined through training of the historical data set, and an accurate evaluation model can be formed finally to evaluate the load impact condition of the fan blade under different turbulence conditions, so that powerful data support is provided for the operation and maintenance of the fan.

Optimizing regression coefficients by minimizing errors between predicted and actual values, and finally determining regression coefficients、AndIs a value of (2);

Regression coefficients are optimized by minimizing the error between the predicted and actual values in order to ensure the accuracy and predictive ability of the model. In a multiple regression model, the determination of the regression coefficients directly affects the accuracy of the predicted outcome. Each regression coefficient represents the degree of influence of the independent variable on the dependent variable, and therefore, the value of the regression coefficient must be continuously adjusted by comparing the difference between the load impact coefficient predicted by the model and the actual observed value. To achieve this goal, a least squares method (Least Squares Method) is typically used as an optimization method that solves for the optimal regression coefficients by minimizing the sum of squares of the differences between all predicted and actual values. Specifically, by constructing an error square sum function, turbulence stress intensity coefficients and instantaneous load impact coefficients of each region in the historical data set are substituted into a model, errors between the corresponding load impact coefficients and actual observed values are calculated, and then regression coefficients are adjusted so that the errors are minimized. Through the continuous iteration process, the optimal values of three regression coefficients can be obtained, so that the model can be ensured to accurately evaluate the instantaneous load impact degree of turbulence on the fan blade, and the safety and efficiency of fan operation are improved.

Inputting turbulence stress intensity coefficients of each region generated in real time to a constructed turbulence influence evaluation model by using the finally determined regression coefficientsAnd transient load impact coefficientGenerating load impact coefficients of all areas in real time。

In the present embodiment, the load impact coefficient for each region generatedAnalysis is performed to generate impact assessment indexAccording to the formula: and the generated impact evaluation index With a preset impact evaluation index threshold intervalThe instantaneous load impact degree of turbulence on the fan blade is evaluated according to the comparison result, and the instantaneous load impact degree is divided into three types of low load impact, medium load impact and high load impact according to the evaluation result, wherein the specific comparison analysis and division are as follows:

When the impact assessment index is less than the minimum value of the preset impact assessment index threshold interval, the transient load impact degree of the turbulence to the fan blade is lower. At this time, the fan blade is subjected to less air flow disturbance, the strength of turbulence is relatively weak, the bending and vibration degree of the blade is low, and the influence of load impact on the mechanical stress of the blade is small. For the running of the fan, the condition shows that the blades are in a stable state in the running process, the efficiency and the safety of the fan are high, excessive adjustment or protection measures are not needed, and the fan can maintain normal running with high running efficiency. At this time, the fan can continue to normally run, unnecessary shutdown or adjustment is reduced, and the stability and the productivity of the whole system are improved.

If it isThe instantaneous load impact degree of the turbulence on the fan blade is the medium range degree, and the medium load impact is divided;

When the impact assessment index is within a predetermined impact assessment index threshold interval, this means that the instantaneous load impact of turbulence on the fan blade is moderate. At this time, the influence of turbulence gives rise to a significant impact on the blade, resulting in a degree of vibration and bending of the blade, and uneven airflow may cause localized fatigue of the blade. Although the impact of the load on the blade is less, the stability of the fan system is already at this point compromised. If this condition is maintained, it may cause progressive blade damage, affecting the efficiency and life of the fan. In such a case, the fan may need to adjust operating parameters (such as rotational speed or direction) to reduce turbulence effects, avoiding further mechanical damage or efficiency losses.

If it isThe turbulence divides the instantaneous load impact of the fan blade into high load impacts if it is high.

When the impact assessment index is greater than the maximum value of the preset impact assessment index threshold interval, the instantaneous load impact degree of the turbulence on the fan blade is higher. At this time, the fan blade is subjected to strong load impact, and the turbulence effect causes the blade to bend, deform or vibrate to a large extent, which may generate significant mechanical stress on the structure of the blade, and even cause fatigue damage or fracture of the blade. If the fan is in such a high load impact condition for a long period of time, the risk of damage to the blades will increase significantly, possibly resulting in a shutdown of the fan, or in the need for urgent maintenance and adjustment. Under such circumstances, the fans need to take protective measures, such as speed reduction, shutdown or blade angle adjustment, to avoid further damage, and at the same time, the operation strategy of the fans needs to be optimized in real time to reduce the negative effects of turbulence and ensure the safety and long-term operation stability of the fans.

The "preset impact assessment index threshold interval" may be determined by a data driven method, i.e. a statistical analysis or a machine learning algorithm is used to set a suitable threshold interval based on historical operating data and actual operating conditions of the fan blades. In particular, a large amount of historical data can be collected firstly, wherein the historical data comprise the operation state data of the fan blade under different climatic conditions, different turbulence intensity and load impact conditions, such as information of curvature, vibration frequency, stress change and the like of the blade. By analyzing the data, impact assessment indices under different circumstances can be calculated and statistical methods (e.g., quantile analysis, standard deviation) can be used to determine a reasonable range of impact assessment indices. In addition, the relation between the impact evaluation index and parameters such as damage, efficiency change and the like of the fan blade can be modeled through a machine learning model (such as cluster analysis or regression analysis), so that the performance change of the blade under different load impacts is predicted. These models may help identify the impact of different load impacts on the fan blade, and thus determine the appropriate threshold interval. By the method, the threshold interval can be dynamically optimized, and the threshold can be updated according to real-time data, so that the best operation protection and scheduling strategy of the fan can be ensured under different working conditions.

In this embodiment, according to the division result, corresponding measures are respectively taken for the fan blades under the conditions of low load impact, medium load impact and high load impact, specifically:

Under the condition of low load impact, the current running state of the fan blade can be maintained by a real-time monitoring system and state maintaining logic. Specifically, the running state of the fan blade comprises the rotating speed, the blade angle and the current load condition, and the data are collected through the sensor and then transmitted to the central control system. The software will analyze the sensor data in real time to determine if the current impact assessment index is within the low load impact range. If the results confirm that the low load impact range is met, the system will execute a "state hold" logic, i.e., maintain the current speed and blade angle, avoiding unnecessary adjustments. Meanwhile, the load condition of the blade is monitored in real time by means of software setting, timely collecting sensor data and dynamically comparing the sensor data with an impact evaluation index so as to ensure that the fan blade operates in a safe load range. The design can avoid excessive adjustment under the condition of low impact, improve the operation efficiency of the system and reduce the extra mechanical stress on the fan blade.

For the fan blade under the condition of medium load impact as a dividing result, the method adopts the steps of adjusting the operation parameters of the fan, reducing load fluctuation, optimizing the load distribution of the blade, continuously monitoring the operation state of the blade, and ensuring that the blade operates under the optimal working condition.

In the case of medium load impact, load fluctuations are reduced by adjusting the operating parameters of the fan and the load distribution of the blades is optimized. This may be achieved by a parameter dynamic adjustment module in the fan control system. Specifically, software needs to dynamically calculate the optimal rotational speed and blade angle of the fan blade based on real-time sensor data (e.g., turbulence stress intensity coefficient and instantaneous load impact coefficient) to reduce the load impact caused by turbulence. For example, the system may optimize aerodynamic performance by adjusting the windward angle of the blade, reducing the impact of uneven turbulence on the blade surface. Meanwhile, the software judges whether the load distribution is reasonable or not through monitoring the vibration frequency and the load fluctuation amplitude, and optimizes the load adjustment strategy according to an algorithm. The purpose of doing so is to reduce fatigue damage when guaranteeing fan blade normal operating, extension blade life improves fan operation's stability and efficiency.

The method comprises the steps of immediately starting a protection mechanism, rapidly reducing the rotating speed of the fan, avoiding the blade bearing impact force, improving the steady-state support of a fan tower through automatic scheduling of a system, sharing the load pressure of the blade, simultaneously monitoring vibration and stress data of the fan blade in real time, early warning abnormal conditions, starting an emergency shutdown program, taking protection measures, and preventing the blade from faults such as excessive wear or fracture.

In the case of high load impact, the damage to the blade is prevented by immediately starting the protection mechanism, reducing the rotational speed, and monitoring the blade condition in real time. Implementing this approach requires automatic detection and response logic that relies on high load impacts. When the impact evaluation index exceeds a set high load threshold, the system triggers an emergency protection program to preferentially reduce the rotating speed of the fan so as to lighten the impact force born by the blades. Meanwhile, the system can adjust the blade angle through the dynamic scheduling module or start auxiliary structures (such as tower supports) to share the blade load pressure, so that the mechanical stress caused by load concentration is further reduced. In addition, vibration and stress data of the blade are monitored in real time through a sensor network, and the data are compared with an early warning threshold under a high-load condition after being transmitted to a software analysis module. Once an abnormal signal (e.g., vibration frequency exceeding a threshold or a sudden increase in stress) is detected, the system will initiate an emergency shutdown procedure and generate a protective action report. The design can protect the structural integrity of the fan blade and the tower under the high-load impact condition, avoid the occurrence of catastrophic failure and ensure the long-term operation safety of the fan.

Continuous monitoring of the operational status and turbulence effects of the fan blades can be achieved by deploying a distributed sensor network and a real-time data acquisition system. Specifically, a plurality of sensors (such as a strain sensor, an acceleration sensor, a wind speed sensor and a pressure sensor) are installed in different areas of the fan blade, and the sensors can capture vibration, stress, bending and surrounding turbulence intensity changes of the blade in real time. The data are transmitted to a central control system through a wireless network or a wired network, and software integrates and pre-processes the sensor data (such as noise filtering and signal standardization) by utilizing a data acquisition module. By the mode, the system can grasp the running state of the blade and the influence condition of turbulence on the blade in real time, and reliable data support is provided for subsequent analysis. The design of continuous monitoring can ensure the transparency of the running state of the fan, so that the system can catch potential risks or anomalies at any time and provide timely protection and optimization measures.

The turbulence influence evaluation model and the fan scheduling strategy are dynamically adjusted according to the real-time monitoring data, and the turbulence influence evaluation model and the fan scheduling strategy can be realized through an adaptive model and a real-time optimization algorithm. Specifically, the software needs to input the turbulence intensity, instantaneous load impact and running state data of the fan blade monitored in real time into a turbulence influence evaluation model, and compare the output result of the model with the actual monitored data. If the evaluation result deviates from the actual running data, the system adjusts parameters of the turbulence influence evaluation model, such as regression coefficients, threshold intervals and the like, through the dynamic optimization module so as to ensure that the model can accurately reflect the stress condition of the blade under the current turbulence condition. Meanwhile, the fan scheduling strategy dynamically adjusts key parameters such as fan rotating speed, blade angle and the like by analyzing the current load distribution of the blades and combining the output result of the model, so that the running state of the fan is optimized. This dynamic tuning mechanism enables models and strategies to be adapted to real-time varying turbulent environments at all times, avoiding operational problems due to evaluation errors or hysteresis.

The method is characterized in that the running state and turbulence influence of the fan blades are continuously monitored, and an evaluation model and a scheduling strategy are dynamically adjusted so as to ensure that the fan can run safely and efficiently under complex and dynamically-changed turbulence conditions. The temporal and spatial non-uniformity of turbulence can lead to increased fluctuation in blade loading, which, if not accurately assessed and adjusted in time, can lead to damage to the blade structure or reduced efficiency. By means of real-time monitoring data and a dynamic adjustment mechanism, the system can update the evaluation result and the operation strategy rapidly when the turbulence condition changes, so that transient load impact of turbulence on the blade is reduced, and mechanical failure or efficiency loss caused by lag or inaccuracy of an evaluation model is prevented. In addition, the design can prolong the service life of the fan blade and key parts, reduce the maintenance cost, improve the economical efficiency and the safety of the operation of the fan, and finally realize the intelligent operation and maintenance target of the fan.

The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.

The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired or wireless means (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.

It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the several embodiments provided in the present application, it should be understood that the disclosed system and method may be implemented in other manners. For example, the embodiments described above are merely illustrative, e.g., the division of the elements is merely a logical functional division, and there may be additional divisions in actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. The intelligent operation and maintenance management method for the energy technology based on the low-altitude field is characterized by comprising the following steps of:

2. The intelligent operation and maintenance management method based on the energy technology in the low-altitude field according to claim 1, wherein the analysis of the acquired operation state information of each area of the fan blade respectively generates a turbulence stress intensity coefficient and an instantaneous load impact coefficient of each area, and specifically comprises the following steps:

3. The intelligent operation and maintenance management method based on the energy technology in the low-altitude field according to claim 2, wherein the logic for acquiring the turbulence stress intensity coefficient of each area is as follows:

4. The intelligent operation and maintenance management method based on the energy technology in the low-altitude field according to claim 3, wherein the logic for acquiring the instantaneous load impact coefficients of each area is as follows:

in the formula, Is the firstInstantaneous load impact coefficient of each zone.

5. The intelligent operation and maintenance management method based on the energy technology in the low-altitude field according to claim 4, wherein a turbulence influence evaluation model is constructed for the generated turbulence stress intensity coefficient and the instantaneous load impact coefficient of each area, and the load impact coefficient of each area is generated, specifically comprising the following steps:

in the formula, 、AndIs a regression coefficient;

6. The intelligent operation and maintenance management method based on the energy technology in the low-altitude field according to claim 5, wherein the load impact coefficients of the generated areas areAnalysis is performed to generate impact assessment indexAccording to the formula: and the generated impact evaluation index With a preset impact evaluation index threshold intervalThe instantaneous load impact degree of turbulence on the fan blade is evaluated according to the comparison result, and the instantaneous load impact degree is divided into three types of low load impact, medium load impact and high load impact according to the evaluation result, wherein the specific comparison analysis and division are as follows:

7. The intelligent operation and maintenance management method based on the energy technology in the low-altitude field according to claim 6, wherein corresponding measures are respectively taken for fan blades under the conditions of low load impact, medium load impact and high load impact according to the division result, specifically: