CN120593661A - System and method for detecting runner eccentricity of hydro-turbine generator set based on optical fiber monitoring - Google Patents
System and method for detecting runner eccentricity of hydro-turbine generator set based on optical fiber monitoringInfo
- Publication number
- CN120593661A CN120593661A CN202510832574.3A CN202510832574A CN120593661A CN 120593661 A CN120593661 A CN 120593661A CN 202510832574 A CN202510832574 A CN 202510832574A CN 120593661 A CN120593661 A CN 120593661A
- Authority
- CN
- China
- Prior art keywords
- optical fiber
- eccentricity
- rotating wheel
- sensor
- pressure
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/26—Measuring arrangements characterised by the use of optical techniques for measuring angles or tapers; for testing the alignment of axes
- G01B11/27—Measuring arrangements characterised by the use of optical techniques for measuring angles or tapers; for testing the alignment of axes for testing the alignment of axes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/22—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring angles or tapers; for testing the alignment of axes
- G01B21/24—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring angles or tapers; for testing the alignment of axes for testing alignment of axes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H9/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
- G01H9/004—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means using fibre optic sensors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L1/00—Measuring force or stress, in general
- G01L1/24—Measuring force or stress, in general by measuring variations of optical properties of material when it is stressed, e.g. by photoelastic stress analysis using infrared, visible light, ultraviolet
- G01L1/242—Measuring force or stress, in general by measuring variations of optical properties of material when it is stressed, e.g. by photoelastic stress analysis using infrared, visible light, ultraviolet the material being an optical fibre
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P15/00—Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration
- G01P15/02—Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration by making use of inertia forces using solid seismic masses
- G01P15/03—Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration by making use of inertia forces using solid seismic masses by using non-electrical means
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/20—Hydro energy
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Hydraulic Turbines (AREA)
Abstract
本申请提出了一种基于光纤监测的水轮发电机组转轮偏心率检测系统及方法，涉及水轮发电机组技术领域，包括：压力传感阵列、加速度传感阵列和处理模组；压力传感阵列包括第一光纤压力传感器和多个第二光纤压力传感器，第一光纤压力传感器位于水轮发电机组上冠腔内部，多个第二光纤压力传感器周向均匀分布于水轮发电机组转轮上冠边缘部位；加速度传感阵列包括多个光纤光栅加速度传感器，多个光纤光栅加速度传感器沿不同方向设置于转轮轴承座上；处理模组用于根据各传感器的检测数据确定转轮的偏心方向以及转轮是否处于过偏心状态。通过上述基于光纤监测的水轮发电机组转轮偏心率检测系统可以实现偏心方向与偏心值是否过大的高精度联合判断。
The present application proposes a system and method for detecting the eccentricity of a turbine runner based on optical fiber monitoring, which relates to the technical field of turbine runners and includes: a pressure sensing array, an acceleration sensing array, and a processing module; the pressure sensing array includes a first optical fiber pressure sensor and a plurality of second optical fiber pressure sensors, the first optical fiber pressure sensor being located inside the upper crown cavity of the turbine runner, and the plurality of second optical fiber pressure sensors being evenly distributed circumferentially on the edge of the upper crown of the turbine runner; the acceleration sensing array includes a plurality of optical fiber Bragg grating acceleration sensors, the plurality of optical fiber Bragg grating acceleration sensors being arranged on the runner bearing seat in different directions; the processing module is used to determine the eccentricity direction of the runner and whether the runner is in an over-eccentric state based on the detection data of each sensor. The above-mentioned turbine runner eccentricity detection system based on optical fiber monitoring can realize a high-precision joint judgment of the eccentricity direction and whether the eccentricity value is too large.
Description
Technical Field
The application relates to the technical field of hydroelectric generating sets, in particular to a hydroelectric generating set runner eccentricity ratio detection system and method based on optical fiber monitoring.
Background
In recent years, with the continuous increase of single-machine capacity and unit size of a giant mixed-flow hydroelectric generating set, various problems of serious abrasion, vibration and the like of the hydroelectric generating set are caused. The rotating wheel is used as a key component in the hydroelectric generating set, if eccentricity exists during installation or the eccentricity is generated during operation, a series of problems are caused, the eccentricity is too large, the gap size is changed, the change can influence the characteristic of a flow field around the rotating wheel, the pressure of a crown cavity is obviously changed, and meanwhile, the bearing seat of the rotating wheel is obviously vibrated. Such eccentricity can lead to fatigue failure of the unit structure, increase of unit vibration and power swing, and even endanger safe and stable operation of the power station. Therefore, it is necessary to monitor whether the wheel eccentricity is excessive.
The current rotating wheel eccentricity ratio detection method mainly adopts a contact type measurement mode, the deviation is manually measured by a traditional mode of combining a circle measuring frame or a piano wire with an inside micrometer, the methods need special equipment for measurement, and the measurement precision and the reliability are difficult to be ensured by adopting a manual observation mode, meanwhile, the mode cannot realize dynamic monitoring, the eccentric condition of the rotating wheel cannot be judged in real time, and hidden danger exists in the operation of the rotating wheel.
Disclosure of Invention
In view of the above, the application provides a hydroelectric generating set runner eccentricity ratio detection system and method based on optical fiber monitoring.
In a first aspect, the application provides a hydroelectric generating set runner eccentricity detection system based on optical fiber monitoring, which comprises a pressure sensing array, an acceleration sensing array and a processing module;
the pressure sensing array comprises a first optical fiber pressure sensor and a plurality of second optical fiber pressure sensors, the first optical fiber pressure sensor is positioned in an upper crown cavity of the hydroelectric generating set, and the second optical fiber pressure sensors are circumferentially and uniformly distributed at the edge part of the upper crown of the runner of the hydroelectric generating set;
the acceleration sensing array comprises a plurality of fiber bragg grating acceleration sensors, and the plurality of fiber bragg grating acceleration sensors are arranged on the runner bearing seat along different directions;
The processing module is respectively connected with the first optical fiber pressure sensor, the second optical fiber pressure sensors and the optical fiber grating acceleration sensors, and is used for acquiring detection data of the first optical fiber pressure sensors, the second optical fiber pressure sensors and the optical fiber grating acceleration sensors, and determining the eccentric direction of the rotating wheel and whether the rotating wheel is in an eccentric state or not according to the detection data of the sensors.
In an embodiment, the processing module is further configured to determine a pressure change trend of each second optical fiber pressure sensor according to detection data of each second optical fiber pressure sensor by using a Holt linear trend method, determine the second optical fiber pressure sensor with the pressure change trend being increased and decreased as a target sensor, and determine an eccentric direction of the rotating wheel according to an azimuth of the target sensor.
In an embodiment, the processing module is further configured to obtain finite element simulation data of the rotating wheel in a plurality of eccentric states, compare the detection data of each sensor with the finite element simulation data in each eccentric state, and determine whether the rotating wheel is in an over-eccentric state according to a comparison result, where the finite element simulation data includes pressure data and vibration data.
In an embodiment, the processing module is further configured to perform a first preprocessing on the detection data of the first fiber bragg pressure sensor to generate a first feature vector, perform a second preprocessing on the detection data of each fiber bragg grating acceleration sensor to generate a second feature vector, and input the first feature vector and the second feature vector into a pre-trained eccentric prediction model to obtain an eccentric grade of the rotating wheel, where the eccentric prediction model is an MPA-SVM model.
In an embodiment, the processing module is further configured to perform wavelet denoising on the detection data of the first optical fiber pressure sensor, take pressure data at the first optical fiber pressure sensor obtained when the simulated eccentricity is a first eccentricity and a second eccentricity as the first feature vector, perform wavelet denoising and CEEMDAN decomposition on vibration data of each optical fiber grating acceleration sensor to obtain a plurality of IMF components, screen effective IMF components with correlation coefficients higher than a threshold, and acquire energy distribution, waveform morphology and frequency change of signals under different time and frequency according to the screened effective IMF components, so as to form the second feature vector, where the second eccentricity is greater than the first eccentricity.
In one embodiment, the crown and the center of the main shaft of the hydroelectric generating set are provided with air-supplementing holes, the crown air-supplementing holes and the center of the main shaft are coaxial, and the air delivery is realized through a cavity in the main shaft;
The processing module comprises a wireless demodulator and a processing module which are in wireless communication connection, wherein the first optical fiber pressure sensor and the second optical fiber pressure sensors are respectively and correspondingly connected with the wireless demodulator through a plurality of first transmission optical cables, the first transmission optical cables led out from the crown are led out to a connection flange of the rotating wheel and the main shaft along reserved maintenance gaps and enter a main shaft air-filling hole channel through the sealed threading hole, are axially arranged along the central air-filling hole of the main shaft, and are connected to the wireless demodulator arranged at the top of the air-filling valve of the generator layer in an extending mode.
In one embodiment, the number of the second fiber optic pressure sensors is eight, the number of the fiber optic grating acceleration sensors is three, and the three fiber optic grating acceleration sensors are respectively arranged on the runner bearing seat along the vertical direction, the axial direction and the horizontal direction.
In a second aspect, the present application further provides a method for detecting eccentricity of a hydroelectric generating set runner based on optical fiber monitoring, where the method for detecting eccentricity of a hydroelectric generating set runner based on optical fiber monitoring is applied to the system for detecting eccentricity of a hydroelectric generating set runner based on optical fiber monitoring according to the first aspect, and the system comprises:
Acquiring detection data of the first optical fiber pressure sensor, the second optical fiber pressure sensors and the fiber bragg grating acceleration sensors;
and determining the eccentric direction of the rotating wheel and whether the rotating wheel is in an over-eccentric state according to the detection data of each sensor.
In one embodiment, determining the eccentric direction of the wheel based on the detection data of each sensor includes:
determining the pressure change trend of each second optical fiber pressure sensor by a Holt linear trend method according to the detection data of each second optical fiber pressure sensor, and determining the second optical fiber pressure sensor with the pressure change trend from increasing to decreasing as a target sensor;
An eccentric direction of the wheel is determined based on the orientation of the target sensor.
In one embodiment, determining whether the wheel is in an over-eccentric state based on detection data of each sensor includes:
Acquiring finite element simulation data of the rotating wheel in a plurality of eccentric states, wherein the finite element simulation data comprise pressure data and vibration data;
And comparing the detection data of each sensor with the finite element simulation data in each eccentric state, and determining whether the rotating wheel is in an over-eccentric state according to the comparison result.
Compared with the related technology, the hydroelectric generating set runner eccentricity ratio detection system based on optical fiber monitoring has the following beneficial effects:
1. According to the application, the first optical fiber pressure sensors are arranged in the upper crown cavity of the hydroelectric generating set, the second optical fiber pressure sensors are circumferentially and uniformly arranged at the edge part of the upper crown of the runner of the hydroelectric generating set, and the optical fiber grating acceleration sensors are arranged on the runner bearing seat, so that the optical fiber pressure sensors can monitor the pressure change of the upper crown cavity of the hydroelectric generating set, and the optical fiber grating acceleration sensors can monitor the vibration data of the runner. On the basis, the processing module can determine the eccentric direction of the rotating wheel and whether the rotating wheel is in an over-eccentric state according to the detection data of each sensor, so that the real-time monitoring of the rotating wheel eccentricity of the hydroelectric generating set is realized, the high-precision combined judgment of whether the eccentric direction and the eccentric value are over-large is realized by adopting a multi-mode data fusion method, and a specific basis is provided for a worker to timely adjust the installation position of the rotating wheel and check the reason for the deviation of the rotating wheel.
2. The application adopts the optical fiber pressure sensor to monitor the pressure change of the crown cavity of the hydroelectric generating set, adopts the optical fiber grating acceleration sensor to monitor the vibration data of the rotating wheel, and can stably work under the working condition of high noise due to the strong electromagnetic interference resistance and the water noise resistance of the optical fiber sensor, so the optical fiber pressure sensor and the optical fiber grating acceleration sensor have high measurement precision and good long-term reliability. Therefore, the high-precision optical fiber sensing is adopted to monitor the pressure of the crown cavity on the rotating wheel and the vibration at the bearing seat of the rotating wheel in real time, so that the real-time and accurate acquisition of the pressure and vibration data is realized, and the accuracy of the eccentric detection of the rotating wheel of the hydroelectric generating set is further improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for those skilled in the art.
FIG. 1 is a schematic diagram of a system for detecting eccentricity of a rotor wheel of a hydroelectric generating set based on optical fiber monitoring according to an embodiment of the present application;
FIG. 2 is a schematic diagram of an eccentric process of a rotor according to an embodiment of the present application;
FIG. 3 is a schematic diagram showing the distribution of a first fiber optic pressure sensor and a second fiber optic pressure sensor in a pressure sensing array according to an embodiment of the present application;
FIG. 4 is a schematic diagram illustrating a wiring of an optical cable through a main shaft air vent according to an embodiment of the present application;
Fig. 5 is a flow chart of a method for detecting eccentricity of a rotor of a hydro-generator set based on optical fiber monitoring according to an embodiment of the application.
Detailed Description
The following description of the embodiments of the present application will clearly and fully describe the technical aspects of the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, are intended to fall within the scope of the present application.
In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present application and simplifying the description, and do not indicate or imply that the device or element being referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present application.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
In the present application, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed, mechanically connected, electrically connected, directly connected, indirectly connected through an intervening medium, or in communication between two elements or in an interaction relationship between two elements, unless otherwise explicitly specified. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art according to the specific circumstances.
In some embodiments, as shown in fig. 1, the system for detecting the eccentricity of the rotating wheel of the hydroelectric generating set based on optical fiber monitoring provided by the application comprises a pressure sensing array 11, an acceleration sensing array 12 and a processing module 13.
The pressure sensing array 11 comprises a first optical fiber pressure sensor 111 and a plurality of second optical fiber pressure sensors 112, wherein the first optical fiber pressure sensor 111 is positioned in the upper crown cavity of the hydroelectric generating set, and the plurality of second optical fiber pressure sensors 112 are circumferentially and uniformly distributed at the edge part of the upper crown of the runner of the hydroelectric generating set. The acceleration sensor array 12 includes a plurality of fiber bragg grating acceleration sensors 121, and the plurality of fiber bragg grating acceleration sensors 121 are disposed on the wheel bearing seat along different directions.
The processing module 13 is respectively connected with the first optical fiber pressure sensor 111, the second optical fiber pressure sensors 112 and the optical fiber grating acceleration sensors 121, and the processing module 13 is used for acquiring detection data of the first optical fiber pressure sensor 111, the second optical fiber pressure sensors 112 and the optical fiber grating acceleration sensors 121, and determining the eccentric direction of the rotating wheel and whether the rotating wheel is in an eccentric state or not according to the detection data of the sensors.
The optical fiber sensor has strong electromagnetic interference resistance and water noise resistance, can still stably work under the high-noise working condition, and has high measurement precision and long-term reliability of the optical fiber pressure sensor and the optical fiber grating acceleration sensor 121. Therefore, the embodiment adopts high-precision optical fiber sensing to monitor the pressure of the crown cavity on the rotating wheel and vibration at the bearing seat of the rotating wheel in real time, realizes real-time and accurate acquisition of pressure and vibration data, and can improve the accuracy of eccentric detection of the rotating wheel of the hydroelectric generating set.
Illustratively, the first and second fiber optic pressure sensors 111, 112 may employ quartz diaphragm type fiber optic F-P cavity sensors. Light emitted by the light source vertically enters the end face of the optical fiber through the conducting optical fiber, a part of light power is reflected by the end face of the conducting optical fiber, the rest of light power reaches the pressure sensitive film after being transmitted, the light reflected by the inner surface of the sensitive film is partially reflected and coupled back into the conducting optical fiber, the reflected light of the end face of the optical fiber interferes with the reflected light of the inner surface of the pressure sensitive film, when the upper crown is subjected to external flow field change, the generated pressure acts on the diaphragm, the cavity length L of the F-P cavity is changed, interference spectrum change is caused, and the calculation formula of the reflection spectrum is as follows:
Wherein I represents total light intensity after superposition of the reflected light, AndIn order to respectively reflect light intensities of two reflecting surfaces of the Fabry-Perot cavity, n is the refractive index of the Fabry-Perot cavity medium, L is the length of the Fabry-Perot cavity,As the wavelength of the light,Is an additional half-wave loss. By measuring the interference spectrum, demodulating the interference spectrum, the amount of change in the cavity length can be known from the formula (1)。
According to the principle of elastic mechanics, the pressure is changed from the outsideInduced sensor cavity length variationCan be expressed as ̈:
in the formula (2), E is Young's modulus of the film material; is the Poisson's ratio of the film material, r is the effective radius of the film, and h is the thickness of the film.
As can be seen from formula (2), the cavity length variesProportional to the change in external applied pressure. Therefore, the pressure sensitivity calibration is carried out on the cavity length value of the EFPI optical fiber pressure sensor, the wavelength data are converted into the cavity length data through a demodulation algorithm, and then the measured cavity length value can be converted into the external pressure P through the formula (2), so that the real-time measurement of the pressure at the crown is realized.
A fiber grating (FBG) acceleration sensor may include a mass, a resilient element, and an FBG sensor. The mass block is used for sensing external vibration to generate inertial force, and the elastic element converts the inertial force into strain. When the sensor is fixed on the runner bearing seat and vibrates along with the bearing seat, an elastic system formed by the mass block and the elastic element performs forced vibration, so that the wavelength of the fiber bragg grating adhered on the sensor is shifted, and the vibration information of the runner bearing seat is reflected through light intensity information by means of a proper demodulation technology.
In application, as shown in fig. 2, the geometric distribution of the gap can be changed after the rotating wheel is eccentric, so that the flow speed, the pressure distribution and the flow stability of the fluid are directly affected. When the rotating wheel is eccentric and the eccentricity is smaller, the radial space between the outer edge of the crown of the rotating wheel and the inner wall of the static top cover is slightly reduced along the eccentric direction, but the whole rotating wheel still can maintain certain flow.
The continuity equation is as follows:
Where Q represents the volumetric flow rate of the fluid, a is the cross-sectional area through which the fluid flows, and V is the fluid flow rate. The continuity equation shows that the cross-sectional area a decreases and the flow rate increases as the fluid passes through the narrow gap.
The bernoulli equation is:
where P represents the hydrostatic pressure of the fluid, i.e. the pressure inside the fluid, Is the fluid density and V is the flow rate. As seen by Bernoulli's equation, an increase in flow velocity results in a decrease in local static pressure, and thus a smaller pressure in the upper crown chamber. While the upper crown edge, the upper crown seal area, is the narrowest point of the gap, the flow resistance increases significantly. Where partial backflow or clogging of the fluid may occur, further exacerbating the local pressure rise. Thus, despite the lower overall pressure of the chamber, the local pressure at the seal will rise gradually due to the flow resistance.
When the eccentricity increases to a certain threshold, the actual gap size of the sealing zone has approached or fallen below the critical value of fluid flow. At this point, the fluid cannot effectively pass through the narrow gap, resulting in a sharp decrease or even stagnation of the flow in this region. According to conservation of mass, the fluid is forced to turn to other areas with larger gaps, and the pressure in the sealing area suddenly drops due to insufficient flow, forming a low pressure area. The cross-sectional area of the fluid flow increases on the side opposite the eccentric gap, i.e., the region of greater gap, and the fluid flow rate decreases and the static pressure increases in accordance with the Bernoulli equation. At the same time, as the seal areas are blocked from flowing, the fluid redistributes within the cavity, and some of the kinetic energy is converted into pressure energy, further increasing the static pressure in these areas. As the eccentricity value continues to increase, the high-pressure region range gradually expands.
In summary, when the eccentricity of the runner is increased gradually, the pressure in the region with smaller gap of the upper crown cavity is increased gradually, and when the eccentricity of the runner exceeds a certain threshold (for example, 0.5 mm), the pressure of the region with smaller gap of the upper crown cavity is changed from a high pressure region to a low pressure region, and the high pressure region in the upper crown cavity is increased continuously because the fluid cannot flow into the region with smaller gap. Meanwhile, when the eccentric value of the rotating wheel is too large, obvious vibration can be generated at the bearing seat of the rotating wheel. Based on the characteristics, the method and the device provided by the application combine the vibration data of the Fiber Bragg Grating (FBG) acceleration sensor to judge so as to improve the accuracy, and the fact that the pressure change of the upper cavity can be generated due to other conditions such as uneven opening degree of the guide vane, geometric abnormality of the vane, blockage of foreign matters and the like is considered. After the fiber pressure sensor and the fiber bragg grating acceleration sensor 121 are arranged in the circumferential direction and the inner part of the crown, the processing module 13 can acquire detection data of the first fiber pressure sensor 111, the second fiber pressure sensors 112 and the fiber bragg grating acceleration sensors 121, and determine the eccentric direction of the rotating wheel and whether the rotating wheel is in an over-eccentric state according to the detection data of the sensors.
The system for detecting the eccentricity of the hydroelectric generating set runner based on optical fiber monitoring comprises a pressure sensing array 11, an acceleration sensing array 12 and a processing module 13, wherein the pressure sensing array 11 comprises a first optical fiber pressure sensor 111 and a plurality of second optical fiber pressure sensors 112, the acceleration sensing array 12 comprises a plurality of optical fiber grating acceleration sensors 121, the first optical fiber pressure sensors 111 are arranged in the upper crown cavity of the hydroelectric generating set, the second optical fiber pressure sensors 112 are circumferentially and uniformly arranged at the edge part of the upper crown of the hydroelectric generating set runner, the optical fiber grating acceleration sensors 121 are arranged on a runner bearing seat, the optical fiber pressure sensors can monitor the pressure change of the upper crown cavity of the hydroelectric generating set, and the optical fiber grating acceleration sensors 121 can monitor vibration data of the runner. On the basis, the processing module 13 can determine the eccentric direction of the rotating wheel and whether the rotating wheel is in an over-eccentric state according to the detection data of each sensor, so that the real-time monitoring of the rotating wheel eccentricity of the hydroelectric generating set is realized, the high-precision combined judgment of whether the eccentric direction and the eccentric value are over-large is realized by adopting a multi-mode data fusion method, and a specific basis is provided for a worker to timely adjust the installation position of the rotating wheel and check the reason for the deviation of the rotating wheel.
In some embodiments, as shown in fig. 3, the number of the second optical fiber pressure sensors 112 is eight, in fig. 3, #1 to #8 are the second optical fiber pressure sensors 112, and #9 is the first optical fiber pressure sensor 111. The number of the fiber bragg grating acceleration sensors 121 is three, and the three fiber bragg grating acceleration sensors 121 are respectively arranged on the runner bearing seat along the vertical direction, the axial direction and the horizontal direction.
It will be appreciated that the number of second fiber optic pressure sensors 112 may be eight, thereby enabling eight-azimuth eccentric detection. The three fiber bragg grating acceleration sensors 121 are respectively arranged on the runner bearing seat along the vertical direction, the axial direction and the horizontal direction, so that acceleration is detected in three different dimensions, the vertical direction sensor can monitor the vibration condition of the equipment in the up-down direction, the axial direction sensor can capture the acceleration change along the shaft, the horizontal direction sensor is responsible for monitoring the vibration on the horizontal plane, and through collaborative monitoring in the three directions, the acceleration information of the runner bearing seat in the space can be comprehensively and accurately obtained, so that richer and reliable data support is provided for subsequent analysis and evaluation of the running state of the equipment.
The detection accuracy of the eccentric direction of the rotating wheel is related to the number of the second optical fiber pressure sensors 112, and the more the second optical fiber pressure sensors 112 are uniformly distributed on the edge part of the crown of the rotating wheel of the hydro-generator set along the circumferential direction, the higher the detection accuracy of the eccentric direction of the rotating wheel. However, since the greater the number of the second optical fiber pressure sensors 112, the higher the cost, the number of the second optical fiber pressure sensors 112 is set to eight, which is only one example of the present application, and other numbers of the second optical fiber pressure sensors 112 may be selected according to actual needs in the application. Likewise, the fiber grating acceleration sensor 121 may be other numbers.
In some embodiments, the processing module 13 is further configured to determine a pressure change trend of each second optical fiber pressure sensor 112 according to the detection data of each second optical fiber pressure sensor 112 by Holt linear trend method, determine the second optical fiber pressure sensor 112 with the pressure change trend being increased and decreased as a target sensor, and determine the eccentric direction of the rotating wheel according to the orientation of the target sensor.
In addition, in consideration of pressure data fluctuation caused by external factors such as water impact, a verification process may be introduced in the pressure change trend calculation process of the present embodiment. Specifically, the collected preprocessed pressure data is synchronously connected with working condition signals such as unit load and guide vane opening and the like. The core processing adopts Holt index smoothing algorithm, and the horizontal component (L_t) and the trend component (T_t) are dynamically updated every time a new data point is received, wherein the trend component continuously tracks the pressure change direction by a smoothing factor of 0.05-0.15. When T_t is detected to be negative from positive rotation, a triple verification mechanism is started, namely firstly, whether the trend intensity exceeds a dynamic threshold value (which is usually set to be 2-3 times of the normal fluctuation range), secondly, the negative trend is confirmed to last for 3-5 sampling points to eliminate transient interference, and finally, the current pressure value is verified to drop more recently by a preset proportion (for example, 0.5%) of a range to ensure the inflection point significance. And the load and the change rate of the opening of the guide vane are analyzed in real time, when the water impact characteristic (such as the load mutation rate exceeding the threshold value) is detected, the judgment threshold value is automatically lifted or the inflection point detection is stopped for a preset time (for example, 10 seconds), so that noise interference caused by external factors is effectively filtered. The inflection point that eventually satisfies all conditions can be regarded as a pressure trend change point due to decentration, thereby judging the decentration direction.
It can be understood that when the eccentricity of the runner is increased gradually, the pressure in the area with smaller gap of the upper crown cavity is increased gradually, and when the eccentricity of the runner exceeds a certain threshold value, the pressure in the area with smaller gap of the upper crown cavity is changed from a high pressure area to a low pressure area because the fluid cannot flow into the area with smaller gap. Based on this characteristic, the characteristic of the pressure change characteristic where the crown space is reduced when the eccentricity value is excessively large can be utilized to indirectly infer the wheel eccentricity direction. And determining the pressure change trend of each second optical fiber pressure sensor 112 according to the detection data of each second optical fiber pressure sensor 112. When the trend of the pressure change of a certain second optical fiber pressure sensor 112 changes from increasing to decreasing, it is indicated that the wheel is eccentric in the direction of the second optical fiber pressure sensor 112, and the sensor is determined as the target sensor. Finally, according to the position of the target sensor, the eccentric direction of the rotating wheel can be determined, so that the detection of the eccentric direction of the rotating wheel is realized.
In some embodiments, the processing module 13 is further configured to obtain finite element simulation data of the rotating wheel in a plurality of eccentric states, compare the detection data of each sensor with the finite element simulation data in each eccentric state, and determine whether the rotating wheel is in an over-eccentric state according to the comparison result, where the finite element simulation data includes pressure data and vibration data.
For example, various eccentric states with eccentric amounts of 0mm, 0.1mm, 0.3mm, 0.5mm, 1mm, 1.5mm may be set, then the hydro-generator set system in each eccentric state is simulated, finite element simulation data of the rotating wheel in the plurality of eccentric states is obtained through finite element simulation, and the finite element simulation data of the rotating wheel in each eccentric state is used as a reference, so that the approximate eccentric range of the rotating wheel may be determined.
Specifically, the processing module 13 may compare the detection data of each sensor (including the first fiber pressure sensor 111 in the pressure sensor array 11 and the fiber grating acceleration sensor 121 in the acceleration sensor array 12) with the finite element simulation data in each eccentric state, and when the detection data is highly matched with the simulation data in a certain eccentric state, it may be determined that the rotating wheel approaches the eccentric state. Based on this, if it is determined that the eccentric range of the wheel is in the over-eccentric state range, it can be determined that the wheel is in the over-eccentric state. For example, an eccentric state in which the eccentric amount is greater than 0.3mm may be determined as an over-eccentric state.
In some embodiments, the processing module 13 is further configured to perform a first preprocessing on the detection data of the first fiber pressure sensor 111 to generate a first feature vector, and perform a second preprocessing on the detection data of each fiber bragg grating acceleration sensor 121 to generate a second feature vector, and input the first feature vector and the second feature vector into a pre-trained eccentric prediction model to obtain an eccentric grade of the rotating wheel, where the eccentric prediction model is an MPA-SVM model.
The MPA-SVM model is a prediction model combining a Marine Predator Algorithm (MPA) and a Support Vector Machine (SVM). MPA algorithm is used to optimize parameters of SVM to improve classification performance and prediction accuracy of the model. The model can learn the mapping relation between the feature vector and the eccentric grade after pre-training.
In application, the detection data of the first optical fiber pressure sensor 111, the second optical fiber sensors and the optical fiber grating acceleration sensors in each eccentric state can be obtained in a simulation mode, then the detection data of each optical fiber sensor is correspondingly preprocessed to be used as training set data, and the training set data is adopted to train the initial eccentric prediction model so as to obtain a trained eccentric prediction model.
It will be appreciated that the first pre-processing and the second pre-processing are specific ways of processing different types of sensor data with the aim of extracting features that are effective in reflecting the operating state of the wheel. The first characteristic vector is generated based on pressure data in the crown cavity of the hydroelectric generating set, and the second characteristic vector is generated based on vibration data of the runner bearing seat in different directions. The processing module 13 can rapidly and accurately evaluate the eccentricity of the rotating wheel by converting the sensor data into the feature vector and inputting the feature vector into the model, and provides important basis for the state monitoring and fault diagnosis of the hydroelectric generating set. The determination of the eccentric grade is beneficial to timely finding out equipment abnormality, and corresponding maintenance measures are adopted to ensure the safe and stable operation of the hydroelectric generating set.
The training data of the eccentric prediction model may also include detection data of each second optical fiber sensor, and the eccentric prediction model is trained by using the detection data of each second optical fiber sensor, so that the eccentric prediction model can predict the eccentric direction of the rotating wheel.
In some embodiments, the processing module 13 is further configured to perform wavelet denoising on the detected data of the first optical fiber pressure sensor 111, take the pressure data at the first optical fiber pressure sensor 111 obtained when the simulated eccentricity is the first eccentricity and the second eccentricity, respectively, as a first feature vector, perform wavelet denoising and CEEMDAN decomposition on the vibration data of each fiber grating acceleration sensor 121, obtain a plurality of IMF components, screen effective IMF components with correlation coefficients higher than a threshold, and perform energy distribution, waveform morphology and frequency variation of the acquired signal at different times and frequencies according to the screened effective IMF components, so as to form a second feature vector.
The second eccentric amount is larger than the first eccentric amount, a state in which the eccentric amount is smaller than the first eccentric amount may be determined as a normal state, an eccentric state in which the eccentric amount is located between the first eccentric amount and the second eccentric amount may be determined as a slight eccentric state, and a state in which the eccentric amount is larger than the second eccentric amount may be determined as a severe eccentric state. Illustratively, the first amount of eccentricity may be 0.1mm and the second amount of eccentricity may be 0.3mm.
In application, the calculation flow for determining the eccentric direction can be input as a model for judging the eccentric direction of the rotating wheel, the eccentric direction prediction is performed by using the training eccentric prediction model, and the training data can be historical data or simulation data.
After wavelet denoising is performed on the data of the first optical fiber pressure sensor 111 and the data of the optical fiber grating acceleration sensor 121, the pressure data at the second optical fiber pressure sensor 112, which are obtained when the simulated eccentricity is the first eccentricity and the second eccentricity respectively, are used as the first feature vector. Meanwhile, the vibration data is subjected to CEEMDAN decomposition to obtain a plurality of IMF components, effective IMFs with correlation coefficients higher than a threshold value (for example, 3%) are screened, and through analysis of the screened IMFs, information such as energy distribution, waveform morphology, frequency change and the like of signals at different times and frequencies can be obtained to form a multidimensional feature vector, and the information is used as a second feature vector. The data obtained by simulation can be used as training set data, and the training set data is used for training the eccentric prediction model to obtain a trained eccentric prediction model.
It can be understood that when the hydroelectric generating set actually works, the vibration sensor and the pressure sensor are deployed near the rotating wheel of the hydroelectric generating set, and vibration signals and pressure data are synchronously acquired. The same processing procedure as the simulation data is executed on the actual data, namely, wavelet denoising is carried out on the detection data of the first optical fiber pressure sensor 111, the pressure data at the first optical fiber pressure sensor 111, which are obtained when the simulation eccentricity is the first eccentricity and the second eccentricity respectively, are used as a first feature vector, wavelet denoising and CEEMDAN decomposition are carried out on the vibration data of each optical fiber grating acceleration sensor 121, a plurality of IMF components are obtained, the effective IMF components with the correlation coefficient higher than the threshold value are screened, and the energy distribution, the waveform morphology and the frequency change of the acquired signals under different time and frequency are carried out according to the screened effective IMF components, so that a second feature vector is formed. And then the obtained first characteristic vector and the second characteristic vector are input into a trained eccentric prediction model, and real-time judgment of the eccentric direction and the eccentric grade is realized through the prediction data output by the eccentric prediction model, so that the eccentric degree of the rotating wheel can be rapidly and accurately estimated, and an important basis is provided for the state monitoring and fault diagnosis of the hydroelectric generating set.
In some embodiments, the crown and the center of the main shaft of the hydroelectric generating set are respectively provided with an air-supplementing hole, the crown air-supplementing hole is coaxial with the center air-supplementing hole of the main shaft, the air delivery is realized through the cavity in the main shaft, and the joint of the rotating wheel and the main shaft flange is provided with a sealed threading hole along the radial direction.
The processing module 13 comprises a wireless demodulator and a processing module which are in wireless communication connection, wherein the first optical fiber pressure sensor 111 and the second optical fiber pressure sensors 112 are respectively and correspondingly connected with the wireless demodulator through a plurality of first transmission optical cables, wherein the first transmission optical cables led out from the crown are led out to the connection flange of the rotating wheel and the main shaft along reserved maintenance gaps, enter the main shaft air-filling hole channel through a sealed threading hole, are axially arranged along the main shaft center air-filling hole, and are connected to the wireless demodulator arranged at the top of the generator layer air-filling valve in an extending mode.
In application, each optical fiber sensor can be welded at a corresponding position, and as the working environment of the rotating wheel is complex and various, the optical fiber pressure sensor can be protected by welding a protective cover outside the sensor, so that the damage to the sensor caused by water flow action and other impurities such as sediment in water is avoided. The optical cable type adopts a high-pressure-resistant and high-temperature-resistant armored optical cable, and the joint of the optical cable and the sensor is protected by adopting a proper sealing ring, so that high-pressure water flow is prevented from entering. The optical cable is fixed by the buckles at intervals and is protected by the stainless steel plate arranged on the surface of the optical cable, so that the stability and the precision of the sensor work are ensured. The rotating wheel is rigidly connected with the main shaft through a flange, the rotation of the rotating wheel transmits torque by virtue of the main shaft, and the upper crown, the blades and the lower ring of the rotating wheel synchronously rotate with the main shaft as a whole. And the upper crown and the center of the main shaft are provided with air-supplementing holes, the air-supplementing holes of the upper crown are coaxial with the air-supplementing holes of the center of the main shaft, and gas delivery is realized through a cavity in the main shaft. Nine first transmission optical cables led out from the upper crown can be led out to the connection flange of the rotating wheel and the main shaft along the reserved maintenance gap. The sealing threading hole along the radial direction is arranged at the joint of the rotating wheel and the main shaft flange, attention needs to be paid to avoiding the flange bolt hole of the rotating wheel and the main shaft, the optical cable enters the main shaft air-filling hole channel through the hole, and the buffer length of the optical cable can be reserved by 10-20 mm at the position of the flange plate, so that abrasion is avoided. And binding the transmission optical cables together at intervals of 200-300 mm by using stainless steel rolling belts, and arranging the transmission optical cables upwards along the air supplementing holes in the center of the main shaft, so that the transmission optical cables are prolonged to the top of the air supplementing valve of the generator layer, and the structural strength is prevented from being weakened by additional holes. And the high-temperature-resistant buckle is used for fixing the transmission optical cable, so that the stability of the working environments of the sensor and the optical cable is ensured, and cable breakage caused by centrifugal force or vibration during high-speed rotation is avoided.
As described above, the rotating wheel is a rotating component, the rotating wheel is rigidly connected with the main shaft through the flange, the rotation of the rotating wheel depends on the main shaft to transmit torque, the upper crown, the blades and the lower ring of the rotating wheel rotate synchronously with the main shaft as a whole, the infinite demodulation device can be installed and fixed on the top of the air compensating valve, and rotate along with the main shaft rotating wheel, the first transmission optical cable is connected to the wireless demodulation device, and referring to fig. 4, the layout of the first transmission optical cable 21 in the air compensating hole 22 in the center of the main shaft can be shown in fig. 4. The wireless demodulator receives the data measured by the optical fiber pressure sensor, realizes wireless transmission of the data of the optical fiber pressure sensor, and transmits the data acquired by the demodulator to the processing module in a wireless mode.
It should be noted that, the processing module 13 may further include a processing module of a static demodulator, and the static demodulator may be connected to the processing module in a wired manner. It should be noted that, the wheel bearing seat is a stationary component, so the fiber bragg grating acceleration sensor 121 may be directly led out through the second transmission optical cable and connected to an external static demodulator. The static demodulator demodulates the detection data of the fiber bragg grating acceleration sensor 121 and transmits the demodulated detection data to the processing module, and the processing module combines the pressure data transmitted by the wireless demodulator and the vibration data transmitted by the static demodulator to realize eccentric monitoring.
Based on the same inventive concept, the application also provides a hydro-generator set runner eccentricity detection method based on optical fiber monitoring, which is applied to the hydro-generator set runner eccentricity detection system based on optical fiber monitoring according to any scheme, as shown in fig. 5, and comprises the following steps S501 and S502.
S501, acquiring detection data of a first optical fiber pressure sensor, second optical fiber pressure sensors and optical fiber grating acceleration sensors.
S502, determining the eccentric direction of the rotating wheel and whether the rotating wheel is in an over-eccentric state according to the detection data of each sensor.
The hydroelectric generating set runner eccentricity detection method based on optical fiber monitoring is applied to the hydroelectric generating set runner eccentricity detection system based on optical fiber monitoring according to any scheme, as the first optical fiber pressure sensors are arranged in the upper crown cavity of the hydroelectric generating set, the second optical fiber pressure sensors are circumferentially and uniformly arranged at the edge part of the upper crown of the hydroelectric generating set runner, the optical fiber grating acceleration sensors are arranged on the runner bearing seat, the optical fiber pressure sensors can monitor pressure change of the upper crown cavity of the hydroelectric generating set, and the optical fiber grating acceleration sensors can monitor vibration data of the runner. On the basis, detection data of the first optical fiber pressure sensor, the second optical fiber pressure sensors and the optical fiber grating acceleration sensors are obtained, the eccentric direction of the rotating wheel and whether the rotating wheel is in an over-eccentric state or not are determined according to the detection data of the sensors, real-time monitoring of the rotating wheel eccentricity of the hydroelectric generating set can be achieved, high-precision joint judgment of whether the eccentric direction and the eccentric value are over-large or not is achieved by adopting a multi-mode data fusion method, and a specific basis is provided for a worker to timely adjust the installation position of the rotating wheel and check the reason for the deviation of the rotating wheel.
In some embodiments, determining the eccentric direction of the rotating wheel according to the detection data of each sensor comprises the steps of determining the pressure change trend of each second optical fiber pressure sensor according to the detection data of each second optical fiber pressure sensor by a Holt linear trend method, determining the second optical fiber pressure sensor with the pressure change trend being increased and decreased as a target sensor, and determining the eccentric direction of the rotating wheel according to the direction of the target sensor.
In some embodiments, determining whether the wheel is in an over-eccentric state according to the detection data of each sensor comprises the steps of obtaining finite element simulation data of the wheel in a plurality of eccentric states, wherein the finite element simulation data comprises pressure data and vibration data, comparing the detection data of each sensor with the finite element simulation data in each eccentric state, and determining whether the wheel is in the over-eccentric state according to a comparison result.
In some embodiments, the method for detecting the eccentricity of the rotating wheel of the hydroelectric generating set based on optical fiber monitoring further comprises the steps of performing first preprocessing on detection data of a first optical fiber pressure sensor to generate a first feature vector, performing second preprocessing on detection data of each optical fiber grating acceleration sensor to generate a second feature vector, and inputting the first feature vector and the second feature vector into a pre-trained eccentricity prediction model to obtain the eccentricity grade of the rotating wheel. Wherein the eccentric prediction model is an MPA-SVM model.
In some embodiments, the method comprises the steps of performing first preprocessing on detection data of a first fiber-optic pressure sensor to generate a first feature vector, performing second preprocessing on the detection data of each fiber-optic grating acceleration sensor to generate a second feature vector, performing wavelet denoising on the detection data of the first fiber-optic pressure sensor, taking pressure data at the first fiber-optic pressure sensor obtained when simulated eccentricity is 0.1mm and 0.3mm respectively as the first feature vector, performing wavelet denoising and CEEMDAN decomposition on vibration data of each fiber-optic grating acceleration sensor to obtain a plurality of IMF components, screening effective IMF components with correlation coefficients higher than a threshold value, and performing the steps of acquiring energy distribution, waveform morphology and frequency change of signals at different times and frequencies according to the screened effective IMF components to form the second feature vector.
It should be noted that, the method for detecting the eccentricity of the hydroelectric generating set runner based on optical fiber monitoring provided by the embodiment of the present application is based on the same application conception as the system for detecting the eccentricity of the hydroelectric generating set runner based on optical fiber monitoring provided by the embodiment of the present application, so that the implementation of the embodiment can be referred to the implementation of the foregoing system for detecting the eccentricity of the hydroelectric generating set runner based on optical fiber monitoring, and the repetition is omitted.
In some embodiments, the electronic device provided by the embodiment of the application comprises a processor and a memory, wherein the memory stores a computer program, and the computer program realizes the method for detecting the eccentricity of the rotating wheel of the hydroelectric generating set based on optical fiber monitoring when being executed by the processor.
In particular, the processor may comprise, for example, a general purpose microprocessor, an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. The processor may also include on-board memory for caching purposes. The processor may be a single processing unit or a plurality of processing units for performing the different actions of the method flows according to embodiments of the application.
The memory may be, for example, any medium capable of containing, storing, transmitting, propagating, or transmitting instructions. For example, a memory may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium. Specific examples of memory include magnetic storage devices such as magnetic tape or hard disk (HDD), optical storage devices such as compact disk (CD-ROM), but also Random Access Memory (RAM) or flash memory, and/or wired/wireless communication links.
The application also provides a computer readable medium, on which a computer program is stored, which when being executed by a processor, realizes the method for detecting the eccentricity of the rotating wheel of the hydroelectric generating set based on optical fiber monitoring. The computer readable medium may be embodied in the apparatus/device/system described in the above embodiments or may exist alone without being assembled into the apparatus/device/system. The computer readable medium carries one or more programs which, when executed, implement methods as embodiments of the present application.
According to an embodiment of the present application, the computer readable medium may be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of a computer-readable storage medium may include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, radio frequency signal, etc., or any suitable combination of the foregoing.
Those skilled in the art will appreciate that the features recited in the various embodiments of the application and/or in the claims may be combined in various combinations and/or combinations even if such combinations or combinations are not explicitly recited in the application. In particular, the features recited in the various embodiments of the application and/or in the claims can be combined in various combinations and/or combinations without departing from the spirit and teachings of the application. All such combinations and/or combinations fall within the scope of the application. The scope of the application should, therefore, be determined not with reference to the above-described embodiments, but instead should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. The system for detecting the eccentricity of the rotating wheel of the hydroelectric generating set based on optical fiber monitoring is characterized by comprising a pressure sensing array, an acceleration sensing array and a processing module;
the pressure sensing array comprises a first optical fiber pressure sensor and a plurality of second optical fiber pressure sensors, the first optical fiber pressure sensor is positioned in an upper crown cavity of the hydroelectric generating set, and the second optical fiber pressure sensors are circumferentially and uniformly distributed at the edge part of the upper crown of the runner of the hydroelectric generating set;
the acceleration sensing array comprises a plurality of fiber bragg grating acceleration sensors, and the plurality of fiber bragg grating acceleration sensors are arranged on the runner bearing seat along different directions;
The processing module is respectively connected with the first optical fiber pressure sensor, the second optical fiber pressure sensors and the optical fiber grating acceleration sensors, and is used for acquiring detection data of the first optical fiber pressure sensors, the second optical fiber pressure sensors and the optical fiber grating acceleration sensors, and determining the eccentric direction of the rotating wheel and whether the rotating wheel is in an eccentric state or not according to the detection data of the sensors.
2. The system for detecting the eccentricity of a rotating wheel of a hydroelectric generating set based on optical fiber monitoring according to claim 1, wherein the processing module is further used for determining the pressure change trend of each second optical fiber pressure sensor according to detection data of each second optical fiber pressure sensor by a Holt linear trend method, determining the pressure change trend from the increased/decreased second optical fiber pressure sensor as a target sensor, and determining the eccentricity direction of the rotating wheel according to the orientation of the target sensor.
3. The system for detecting the eccentricity of a rotating wheel of a hydroelectric generating set based on optical fiber monitoring according to claim 1, wherein the processing module is further used for acquiring finite element simulation data of the rotating wheel in a plurality of eccentric states, comparing the detection data of each sensor with the finite element simulation data in each eccentric state, and determining whether the rotating wheel is in an over-eccentric state according to a comparison result, wherein the finite element simulation data comprises pressure data and vibration data.
4. The system for detecting eccentricity of a rotor of a hydroelectric generating set according to claim 1, wherein the processing module is further configured to perform a first preprocessing on detection data of the first optical fiber pressure sensor to generate a first feature vector, perform a second preprocessing on detection data of each optical fiber grating acceleration sensor to generate a second feature vector, and input the first feature vector and the second feature vector into a pre-trained eccentricity prediction model to obtain an eccentricity grade of the rotor, wherein the eccentricity prediction model is an MPA-SVM model.
5. The system for detecting the eccentricity of a rotating wheel of a hydroelectric generating set based on optical fiber monitoring as claimed in claim 4, wherein the processing module is further used for carrying out wavelet denoising on detection data of the first optical fiber pressure sensor, taking pressure data at the first optical fiber pressure sensor obtained when the simulated eccentricity is a first eccentricity and a second eccentricity respectively as the first characteristic vector, carrying out wavelet denoising and CEEMDAN decomposition on vibration data of each fiber grating acceleration sensor to obtain a plurality of IMF components, screening effective IMF components with correlation coefficients higher than a threshold value, and carrying out energy distribution, waveform morphology and frequency change of acquired signals under different time and frequency according to the screened effective IMF components to form the second characteristic vector, wherein the second eccentricity is larger than the first eccentricity.
6. The system for detecting the eccentricity of the rotating wheel of the hydroelectric generating set based on optical fiber monitoring as claimed in claim 1, wherein the crown and the center of the main shaft of the hydroelectric generating set are respectively provided with an air supplementing hole, the crown air supplementing hole is coaxial with the center air supplementing hole of the main shaft, and the air delivery is realized through a cavity in the main shaft;
The processing module comprises a wireless demodulator and a processing module which are in wireless communication connection, wherein the first optical fiber pressure sensor and the second optical fiber pressure sensors are respectively and correspondingly connected with the wireless demodulator through a plurality of first transmission optical cables, the first transmission optical cables led out from the crown are led out to a connection flange of the rotating wheel and the main shaft along reserved maintenance gaps and enter a main shaft air-filling hole channel through the sealed threading hole, are axially arranged along the central air-filling hole of the main shaft, and are connected to the wireless demodulator arranged at the top of the air-filling valve of the generator layer in an extending mode.
7. The system for detecting the eccentricity of a rotating wheel of a hydroelectric generating set based on optical fiber monitoring according to claim 1, wherein the number of the second optical fiber pressure sensors is eight, the number of the optical fiber grating acceleration sensors is three, and the three optical fiber grating acceleration sensors are respectively arranged on the rotating wheel bearing seat along the vertical direction, the axial direction and the horizontal direction.
8. The method for detecting the eccentricity of the rotating wheel of the hydroelectric generating set based on optical fiber monitoring is characterized in that the method for detecting the eccentricity of the rotating wheel of the hydroelectric generating set based on optical fiber monitoring is applied to the system for detecting the eccentricity of the rotating wheel of the hydroelectric generating set based on optical fiber monitoring as claimed in any one of claims 1 to 7, and comprises the following steps:
Acquiring detection data of the first optical fiber pressure sensor, the second optical fiber pressure sensors and the fiber bragg grating acceleration sensors;
and determining the eccentric direction of the rotating wheel and whether the rotating wheel is in an over-eccentric state according to the detection data of each sensor.
9. The method for detecting eccentricity of a rotor of a hydro-generator set based on optical fiber monitoring as recited in claim 8, wherein determining the eccentricity of the rotor based on the detection data of each sensor comprises:
determining the pressure change trend of each second optical fiber pressure sensor by a Holt linear trend method according to the detection data of each second optical fiber pressure sensor, and determining the second optical fiber pressure sensor with the pressure change trend from increasing to decreasing as a target sensor;
An eccentric direction of the wheel is determined based on the orientation of the target sensor.
10. The method for detecting eccentricity of a rotor of a hydro-generator set based on optical fiber monitoring as recited in claim 8, wherein determining whether the rotor is in an over-eccentricity state based on detection data of each sensor comprises:
Acquiring finite element simulation data of the rotating wheel in a plurality of eccentric states, wherein the finite element simulation data comprise pressure data and vibration data;
And comparing the detection data of each sensor with the finite element simulation data in each eccentric state, and determining whether the rotating wheel is in an over-eccentric state according to the comparison result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510832574.3A CN120593661B (en) | 2025-06-20 | 2025-06-20 | Hydroelectric generating set runner eccentricity ratio detection system and method based on optical fiber monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510832574.3A CN120593661B (en) | 2025-06-20 | 2025-06-20 | Hydroelectric generating set runner eccentricity ratio detection system and method based on optical fiber monitoring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120593661A true CN120593661A (en) | 2025-09-05 |
| CN120593661B CN120593661B (en) | 2026-03-17 |
Family
ID=96897242
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510832574.3A Active CN120593661B (en) | 2025-06-20 | 2025-06-20 | Hydroelectric generating set runner eccentricity ratio detection system and method based on optical fiber monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120593661B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107036692A (en) * | 2015-07-15 | 2017-08-11 | 成都阜特科技股份有限公司 | A kind of wind generator set blade icing measuring method |
| CN112523926A (en) * | 2020-12-17 | 2021-03-19 | 中国长江电力股份有限公司 | Hydraulic generator runner pressure monitoring system and method |
| CN214223990U (en) * | 2021-02-02 | 2021-09-17 | 浙江富春江水电设备有限公司 | Intelligent data acquisition and analysis system for turning of hydroelectric generating set |
| CN119982286A (en) * | 2025-01-24 | 2025-05-13 | 中国长江电力股份有限公司 | A mechanical overspeed monitoring system and method for a hydro-generator set |
| CN119989112A (en) * | 2025-01-06 | 2025-05-13 | 华能澜沧江水电股份有限公司 | Anomaly detection and fault diagnosis method of hydraulic turbine based on multi-sensor data fusion |
-
2025
- 2025-06-20 CN CN202510832574.3A patent/CN120593661B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107036692A (en) * | 2015-07-15 | 2017-08-11 | 成都阜特科技股份有限公司 | A kind of wind generator set blade icing measuring method |
| CN112523926A (en) * | 2020-12-17 | 2021-03-19 | 中国长江电力股份有限公司 | Hydraulic generator runner pressure monitoring system and method |
| CN214223990U (en) * | 2021-02-02 | 2021-09-17 | 浙江富春江水电设备有限公司 | Intelligent data acquisition and analysis system for turning of hydroelectric generating set |
| CN119989112A (en) * | 2025-01-06 | 2025-05-13 | 华能澜沧江水电股份有限公司 | Anomaly detection and fault diagnosis method of hydraulic turbine based on multi-sensor data fusion |
| CN119982286A (en) * | 2025-01-24 | 2025-05-13 | 中国长江电力股份有限公司 | A mechanical overspeed monitoring system and method for a hydro-generator set |
Non-Patent Citations (1)
| Title |
|---|
| 武玉才等: "水轮发电机转子不圆度诱发的定子铁心振动特性研究", 中国电机工程学报, vol. 45, no. 1, 5 January 2025 (2025-01-05), pages 342 - 351 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120593661B (en) | 2026-03-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2374010B1 (en) | Turbulence sensor and blade condition sensor system | |
| US9557210B2 (en) | Method for non-intrusive on-line detection of turbine blade condition | |
| ES2637892T3 (en) | Procedure and apparatus for monitoring wind turbine components based on conditions | |
| US10316849B2 (en) | Method and system for detection of faults in pump assembly via handheld communication device | |
| EP2434266B1 (en) | Sideband energy ratio method for gear mesh fault detection | |
| CN105765361B (en) | Bearing monitoring device and method | |
| CA2461973A1 (en) | Sand monitoring within wells using acoustic arrays | |
| US20230206119A1 (en) | Event model training using in situ data | |
| CN103608653A (en) | Wind turbine including optical sensor system | |
| EP3062131B1 (en) | Method for detecting damage of wind turbine blade and wind turbine | |
| US20210123833A1 (en) | Method and system for estimating the wear of a rotating machine including a bearing | |
| IT201800003956A1 (en) | METHOD AND APPARATUS FOR MEASURING THE PROPERTIES OF A LIQUID. | |
| CN111897375A (en) | Ship lock operation dynamic water level monitoring system and monitoring method | |
| JP2017156151A (en) | Torque measuring device, gear box and torque measuring method | |
| CN114293977A (en) | Method for testing driving end perception type pumping unit indicator diagram | |
| WO2025061969A1 (en) | Systems and methods for monitoring and diagnosing industrial equipment | |
| CN120593661B (en) | Hydroelectric generating set runner eccentricity ratio detection system and method based on optical fiber monitoring | |
| CN106932068A (en) | A kind of train dynamic weighing method and device | |
| Haseeb et al. | A State-of-the-Art Review of Structural Health Monitoring Techniques for Wind Turbine Blades | |
| Kushner | Dynamic strain measurement of propeller shaft vibrations | |
| WO2025084931A1 (en) | Installation method and system for monitoring structural response of wind turbine blades | |
| Escaler et al. | Cavitation erosion prediction in hydro turbines from onboard vibrations | |
| Bourdon et al. | Erosion vibratory fingerprint of leading edge cavitation of a Naca profile and of a Francis model and prototype hydroturbine | |
| US12055453B2 (en) | Stress estimation method for machine structure and monitoring method for machine structure | |
| Eaton et al. | Evaluating the Performance Degradation of Centrifugal Pumps Using the Principal Component Analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |