CN-121994341-A - Online monitoring method for abnormal vibration of thermal energy storage equipment

CN121994341ACN 121994341 ACN121994341 ACN 121994341ACN-121994341-A

Abstract

The invention provides an online monitoring method for abnormal vibration of thermal energy storage equipment, which belongs to the technical field of thermal energy storage equipment, and aims to solve the technical problems that a multisource coupling vibration signal is difficult to accurately separate and identify an abnormal vibration mode in the phase change process of the thermal energy storage equipment by arranging a multisource sensor array comprising low-frequency and high-frequency vibration sensors at key positions of the thermal energy storage equipment, adopting a differential arrangement mode to inhibit noise interference, utilizing an independent component analysis algorithm to separate multisource coupling vibration signals, combining wavelet transformation to perform time-frequency analysis to extract vibration characteristics, establishing a phase change vibration characteristic mechanism equation to calculate physical parameter change of materials in the phase change process, constructing a neural network identification model based on dynamic topology reconstruction sparse connection learning and probability graph model structural prediction, and establishing a vibration abnormal judgment threshold system.

Inventors

YANG LEI
ZHANG LEI
XU MEI
ZHANG CHENXI
WANG ZEZHONG
ZHU CHANG
WEI FEI
BAI DINGRONG

Assignees

鄂尔多斯实验室
清华大学

Dates

Publication Date: 20260508
Application Date: 20251203

Claims (10)

1. An on-line monitoring method for abnormal vibration of a thermal energy storage device is characterized in that a multi-source vibration sensor array is arranged at a key position of the thermal energy storage device, multichannel vibration signals and temperature signals are collected for preprocessing and digital filtering, a signal separation matrix is built by separating the multi-source coupling vibration signals based on an independent component analysis algorithm, a vibration characteristic vector set is extracted by wavelet transformation time-frequency analysis of the separated vibration signals, a phase change vibration characteristic parameter set is built by analyzing the influence of physical state change of a phase change material on vibration characteristics by utilizing a phase change vibration characteristic mechanism equation, an abnormal vibration mode is identified by utilizing a phase change vibration characteristic identification model to process the vibration characteristic vector set, temperature data and the phase change vibration characteristic parameter set, an abnormal vibration judgment threshold system is built to trigger an abnormal vibration early warning mechanism, and the working mode and signal processing algorithm parameters of the sensor array are adjusted in a self-adaption mode according to the type and severity of abnormal vibration.
2. The on-line monitoring method for abnormal vibration of a thermal energy storage device according to claim 1, wherein the arranging step of the multi-source vibration sensor array is specifically to arrange a plurality of combinations of different types of vibration sensors on the thermal energy storage device according to a preset spatial distribution rule, wherein the combinations comprise a low-frequency vibration sensor and a high-frequency vibration sensor, the environmental noise interference is reduced by adopting a differential arrangement mode, and meanwhile, a temperature vibration coupling sensor is arranged in a phase change material area and used for comprehensively monitoring the vibration state of the device.
3. The on-line monitoring method of abnormal vibration of a thermal energy storage device according to claim 2, wherein the differential arrangement mode refers to paired installation of sensors of the same type, common-mode noise interference is effectively suppressed by a differential signal processing mode, and the temperature vibration coupling sensor refers to a composite sensor for simultaneously measuring temperature and vibration, and is used for monitoring influence of temperature change on vibration characteristics in a phase change process.
4. The method for on-line monitoring abnormal vibration of a thermal energy storage device according to claim 3, wherein the step of collecting the multi-channel vibration signal and the temperature signal is specifically to synchronously sample by using a high-precision data collecting system, wherein the sampling frequency is set to be 2.56 times of the highest frequency of the vibration signal according to the nyquist sampling theorem, and the collected signals are preprocessed and digitally filtered.
5. The method for on-line monitoring of abnormal vibration of a thermal energy storage device according to claim 4, wherein the independent component analysis algorithm refers to a blind source separation algorithm for decomposing a plurality of mixed signals into statistically independent source signals by a statistical independence principle, and a separation matrix for maximizing statistical independence of the separated signals is found, and the signal separation matrix refers to a linear transformation matrix for transforming the mixed signals into the independent signals in the independent component analysis algorithm.
6. The method for online monitoring abnormal vibration of a thermal energy storage device according to claim 5, wherein the wavelet transformation time-frequency analysis refers to a signal analysis method for performing multi-scale decomposition on a signal by utilizing a wavelet basis function and simultaneously obtaining time information and frequency information of the signal, and the vibration characteristic vector set refers to a characteristic parameter set extracted from the vibration signal and representing vibration states, wherein the characteristic parameter set comprises amplitude characteristics, frequency characteristics, phase characteristics and statistical characteristics.
7. The method for online monitoring abnormal vibration of a thermal energy storage device according to claim 6, wherein the phase-change vibration characteristic mechanism equation is used for describing the rule of influence of physical parameter changes of the phase-change material on vibration characteristics in the phase-change process, and the input includes a current temperature T and a phase-change temperature And outputting a phase change vibration characteristic parameter set, and calculating the material density change rate, the elastic modulus change rate and the damping coefficient change rate in the phase change process.
8. The method for on-line monitoring abnormal vibration of a thermal energy storage device according to claim 7, wherein the phase-change vibration characteristic parameter set refers to a parameter set representing physical characteristic change of a material in a phase-change process, which is calculated by a phase-change vibration characteristic mechanism equation, and comprises a material density change rate, an elastic modulus change rate and a damping coefficient change rate, and the material density change rate refers to a change proportion of a material density relative to an initial density in the phase-change process.
9. The on-line monitoring method for abnormal vibration of a thermal energy storage device according to claim 8, wherein the phase change vibration characteristic identification model refers to a machine learning model for identifying a change rule of vibration characteristics in a phase change process of the thermal energy storage material, and the phase change vibration abnormal probability and the abnormal type identification are output through training and learning a mapping relation between the phase change process and the vibration characteristics, and a value range e [0,1] of the phase change vibration abnormal probability.
10. The method for online monitoring of abnormal vibration of a thermal energy storage device according to claim 9, wherein the phase-change vibration characteristic identification model is in a multi-layer feedforward neural network and comprises an input layer, three hidden layers and an output layer, the input layer receives a vibration characteristic vector set, temperature data and a phase-change vibration characteristic parameter set, the first hidden layer adopts a sparse connection learning framework based on dynamic topology reconstruction, the second hidden layer and the third hidden layer adopt a full connection structure, and the output layer adopts a structured prediction framework based on a probability graph model.

Description

Online monitoring method for abnormal vibration of thermal energy storage equipment Technical Field The invention belongs to the technical field of heat energy storage equipment, and particularly relates to an online monitoring method for abnormal vibration of heat energy storage equipment. Background The thermal energy storage device is used as an important component of a new energy system, and the operation stability of the thermal energy storage device directly influences the energy efficiency performance of the whole system. The traditional vibration monitoring method mainly adopts a single type sensor to collect signals, extracts vibration characteristics through time domain or frequency domain analysis, and utilizes statistical analysis or a simple machine learning algorithm to detect abnormality. The method is widely applied to the fields of industrial equipment state monitoring, rotary machinery fault diagnosis, building structure health monitoring and the like, and can realize the identification of abnormal equipment states to a certain extent. In the current thermal energy storage equipment monitoring technology, because the phase change material can generate complex physical and chemical changes in the solid-liquid phase change process, a plurality of vibration sources are mutually coupled in the equipment, and the traditional single-source signal analysis method cannot effectively process multi-source mixed vibration signals. The prior art generally ignores the influence mechanism of the phase change process on the vibration characteristic, and lacks an analysis model aiming at the change of the physical parameters of the phase change material, so that the abnormal vibration identification accuracy in the phase change process is lower. That is, in the prior art, there is a technical problem that it is difficult to accurately identify an abnormal vibration mode by using a multisource coupled vibration signal in a phase change process of a thermal energy storage device. Disclosure of Invention In view of the above, the invention provides an online monitoring method for abnormal vibration of a thermal energy storage device, which can solve the technical problem that in the prior art, a multisource coupling vibration signal is difficult to accurately identify an abnormal vibration mode in a phase change process of the thermal energy storage device. The invention provides an on-line monitoring method for abnormal vibration of a heat energy storage device, which is realized by arranging a multi-source vibration sensor array at a key part of the heat energy storage device, collecting multi-channel vibration signals and temperature signals, preprocessing and digitally filtering, separating the multi-source coupled vibration signals based on an independent component analysis algorithm to establish a signal separation matrix, performing wavelet transform time-frequency analysis on the separated vibration signals to extract a vibration characteristic vector set, analyzing the influence of physical state change of a phase change material on vibration characteristics by using a phase change vibration characteristic mechanism equation to establish a phase change vibration characteristic parameter set, processing the vibration characteristic vector set, temperature data and the phase change vibration characteristic parameter set by using a phase change vibration characteristic identification model to identify abnormal vibration modes, establishing a vibration abnormal judgment threshold system to trigger an abnormal vibration early warning mechanism, and adaptively adjusting the working mode and signal processing algorithm parameters of the sensor array according to the type and severity of abnormal vibration. The method comprises the step of arranging a multisource vibration sensor array, namely arranging a plurality of vibration sensors of different types on a thermal energy storage device according to a preset space distribution rule, wherein the combination comprises a low-frequency vibration sensor and a high-frequency vibration sensor, environmental noise interference is reduced in a differential arrangement mode, and meanwhile, a temperature vibration coupling sensor is arranged in a phase change material area and used for comprehensively monitoring the vibration state of the device. The differential arrangement mode refers to paired installation of sensors of the same type, common mode noise interference is effectively restrained through a differential signal processing mode, and the temperature vibration coupling sensor refers to a composite sensor for measuring temperature and vibration simultaneously and is used for monitoring the influence of temperature change on vibration characteristics in a phase change process. The method comprises the steps of collecting multichannel vibration signals and temperature signals, and specifically comprises the steps of synchronously sampling by using a high-preci