Search

CN-122015979-A - Sensor-based real-time monitoring method and system for bearing grease injection flow

CN122015979ACN 122015979 ACN122015979 ACN 122015979ACN-122015979-A

Abstract

The invention provides a real-time monitoring method and a system for bearing grease injection flow based on sensors, comprising the steps of obtaining a real-time pressure sequence, a temperature value and an acoustic signal sequence of a grease injection pipeline, calculating a wall adhesion historical factor, calculating a rheological compensation coefficient by using a pressure change rate, the temperature value and the wall adhesion historical factor through a multivariate nonlinear mapping model, obtaining a reference grease injection flow by combining the real-time pressure sequence, the rheological compensation coefficient and a slip compensation coefficient, normalizing the energy attenuation by using the rheological compensation coefficient, correcting the transmission time delay by using the reference grease injection flow for the acoustic signal sequence, constructing a feature matrix, identifying the matrix as a bubble event and estimating the volume if the similarity exceeds a threshold value, correcting the reference grease injection flow in real time, deducting the corresponding flow of the bubble volume, and obtaining the real-time grease injection flow.

Inventors

  • FANG LINJUN

Assignees

  • 河南众正精密轴承有限公司

Dates

Publication Date
20260512
Application Date
20251229

Claims (10)

  1. 1. The real-time monitoring method for the grease injection flow of the bearing based on the sensor is characterized by comprising the following steps of: Acquiring a real-time pressure sequence of a pressure sensor and a real-time temperature sequence of a temperature sensor which are arranged on a fat injection pipeline, and an acoustic signal sequence of an acoustic sensor array axially arranged along the fat injection pipeline; Calculating a wall adhesion history factor based on the fat injection intermittent time length and the estimated volume of the identified bubbles in the previous period, and determining a slip compensation coefficient based on the wall adhesion history factor; calculating a rheological compensation coefficient through a preset multivariable nonlinear mapping model based on the pressure change rate of the real-time pressure sequence, the real-time temperature value and the wall adhesion historical factor; The method comprises the steps of calculating transmission time delay and energy attenuation of acoustic signals between adjacent sensors, normalizing the energy attenuation by using the rheological compensation coefficient, and carrying out time domain correction on the transmission time delay by using the reference fat injection flow, constructing a feature matrix based on the normalized energy attenuation and the corrected transmission time delay, comparing the feature matrix with the similarity of bubble feature modes in a preset mode library, and identifying the bubble event and estimating the volume if the similarity is larger than a preset threshold; and correcting the reference fat injection flow in real time, and deducting the flow corresponding to the estimated volume of the bubble event to obtain the real-time fat injection flow.
  2. 2. The method of claim 1, wherein calculating a wall adhesion history factor based on the estimated volume of identified bubbles for the duration of the fat-filling pause and the last cycle, and determining a slip compensation factor based on the wall adhesion history factor, comprises: Weighting calculation is carried out on the fat injection intermittent time length and the estimated volume of the identified bubbles in the previous period to obtain a wall adhesion historical factor; and determining a slip compensation coefficient through a preset linear relation based on the wall adhesion history factor.
  3. 3. The method of claim 1, wherein the calculating the rheology compensation coefficient by a preset multivariate nonlinear mapping model based on the pressure change rate of the real-time pressure sequence, the real-time temperature value, and the wall adhesion history factor comprises: The multivariable nonlinear mapping model is a feedforward neural network, the input of the network is the pressure change rate of the real-time pressure sequence, the real-time temperature value and the wall adhesion history factor, and the output is the rheological compensation coefficient.
  4. 4. A method according to claim 3, wherein said calculating a reference fat-filling flow rate by combining said real-time pressure sequence, said rheological compensation coefficient and said slip compensation coefficient comprises: The pressure difference delta P of the inlet and the outlet of the grease injection pipeline calculated based on the real-time pressure sequence is combined with the pipeline diameter D, the pipeline length L, the basic viscosity mu of the lubricating grease and the rheological compensation coefficient And the slip compensation coefficient Calculating the reference fat injection flow according to the following formula : 。
  5. 5. The method of claim 1, wherein calculating a propagation time delay and energy attenuation of the acoustic signal between adjacent sensors comprises: calculating the transmission time delay between adjacent sensor signals in the acoustic signal sequence by adopting a generalized cross-correlation-phase transformation method; The energy attenuation of the signal is calculated based on the root mean square energy of the acoustic signals of the adjacent sensors.
  6. 6. The method of claim 1, wherein normalizing the energy decay with the rheology compensation coefficient and time-domain correcting the transit time delay with the reference fat-filled flow comprises: Normalizing the calculated energy attenuation by using the rheological compensation coefficient; And calculating the theoretical transmission time of the acoustic signal based on the reference fat injection flow, and correcting the transmission time delay according to the difference value between the theoretical transmission time and the actually calculated transmission time delay.
  7. 7. The method of claim 1, wherein the comparing the feature matrix with the bubble feature patterns in the library of preset patterns for similarity, if the similarity is greater than a preset threshold, identifying a bubble event and estimating a volume, comprises: calculating the similarity of the characteristic matrix and each bubble characteristic mode in a preset mode library by adopting a cosine similarity algorithm; If the similarity is larger than a preset threshold, identifying the bubble event, and determining the estimated volume of the bubble event based on the energy attenuation characteristics corresponding to the matched bubble characteristic mode through a preset volume-energy attenuation mapping relation.
  8. 8. The method of claim 1, wherein the performing real-time correction on the reference fat injection flow and subtracting the flow corresponding to the estimated volume of the bubble event to obtain the real-time fat injection flow comprises: when a bubble event is identified, calculating the corresponding instantaneous flow of the bubble according to the estimated volume and the transit time of the bubble between the acoustic sensor arrays; And subtracting the instantaneous flow corresponding to the bubble from the reference fat injection flow in the transit time of the bubble to obtain the real-time fat injection flow.
  9. 9. The bearing grease injection flow real-time monitoring system based on the sensor is characterized by comprising the following modules: The device comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring a real-time pressure sequence of a pressure sensor, a real-time temperature sequence of a temperature sensor and an acoustic signal sequence of an acoustic sensor array axially arranged along a fat injection pipeline; The calculation module is used for calculating a wall adhesion history factor based on the fat injection intermittent time length and the estimated volume of the identified bubbles in the previous period, and determining a slip compensation coefficient based on the wall adhesion history factor; calculating a rheological compensation coefficient through a preset multivariable nonlinear mapping model based on the pressure change rate of the real-time pressure sequence, the real-time temperature value and the wall adhesion historical factor; The device comprises a sensor, an identification module, a characteristic matrix, a detection module, a flow rate correction module and a detection module, wherein the sensor is used for detecting the flow rate of the acoustic signal, the identification module is used for calculating the transmission time delay and the energy attenuation of the acoustic signal between adjacent sensors, normalizing the energy attenuation by using the rheological compensation coefficient, and carrying out time domain correction on the transmission time delay by using the reference fat injection flow; and the correction module is used for correcting the reference fat injection flow in real time and deducting the flow corresponding to the estimated volume of the bubble event to obtain the real-time fat injection flow.
  10. 10. The system of claim 9, wherein the calculating a wall adhesion history factor based on the estimated volume of identified bubbles for the duration of the fat injection pause and the last cycle, and determining the slip compensation factor based on the wall adhesion history factor, comprises: Weighting calculation is carried out on the fat injection intermittent time length and the estimated volume of the identified bubbles in the previous period to obtain a wall adhesion historical factor; and determining a slip compensation coefficient through a preset linear relation based on the wall adhesion history factor.

Description

Sensor-based real-time monitoring method and system for bearing grease injection flow Technical Field The application belongs to the field of monitoring, and particularly relates to a real-time monitoring method and system for bearing grease injection flow based on a sensor. Background In the fields of heavy equipment such as wind power, rail transit, metallurgy and the like, the bearing is used as a core transmission part, and good lubrication can enable the bearing to keep a good state. Grease is a high viscosity, non-newtonian fluid, and because of its complex characteristics, accurate metering of the flow becomes a great technical problem in the industry. Existing lipid injection flow monitoring techniques include volumetric methods based on piston displacement and direct measurement methods based on mass flow meters. The volumetric method estimates the fat injection amount by measuring the stroke or the piston displacement of the pump, so that the real-time monitoring of the fat injection process cannot be realized, and abnormal conditions such as pipeline blockage, leakage and the like are difficult to find. The mass flowmeter has high accuracy, but is expensive, large in volume, poor in adaptability to the medium which is high in viscosity and easy to contain solid-phase particles, easy to block and measure drift, and high in maintenance cost. The rheological property of the lubricating grease can be changed along with the change of temperature and pressure, and a wall surface sliding effect can be generated at the pipe wall, so that an error is generated in a pressure-flow calculation method based on a fixed fluid model, and reliable compensation cannot be performed. The grease is prone to air mixing during storage, pumping and transport, forming bubbles of varying sizes. The bubbles can lead to the deficiency of the high readings of the flowmeter, so that the quantity of the lubricating grease actually injected into the bearing is far lower than a set value, the bearing is subjected to false lubrication or under lubrication, and potential safety hazards are brought to equipment. In the prior art, reliable online identification, volume estimation and flow correction are difficult to carry out on bubbles entrained in a high-viscosity medium, so that the accuracy and reliability of the grease injection quantity cannot be guaranteed for a long time, and the requirement of high-end equipment on precise lubrication cannot be met. Disclosure of Invention The invention provides a sensor-based real-time monitoring method for bearing grease injection flow, which is used for solving the problems that bubbles entrained in a high-viscosity medium are difficult to reliably identify on line and estimate the volume and the flow cannot be accurately corrected in the prior art, and comprises the following steps: Acquiring a real-time pressure sequence of a pressure sensor and a real-time temperature sequence of a temperature sensor which are arranged on a fat injection pipeline, and an acoustic signal sequence of an acoustic sensor array axially arranged along the fat injection pipeline; Calculating a wall adhesion history factor based on the fat injection intermittent time length and the estimated volume of the identified bubbles in the previous period, and determining a slip compensation coefficient based on the wall adhesion history factor; calculating a rheological compensation coefficient through a preset multivariable nonlinear mapping model based on the pressure change rate of the real-time pressure sequence, the real-time temperature value and the wall adhesion historical factor; The method comprises the steps of calculating transmission time delay and energy attenuation of acoustic signals between adjacent sensors, normalizing the energy attenuation by using the rheological compensation coefficient, and carrying out time domain correction on the transmission time delay by using the reference fat injection flow, constructing a feature matrix based on the normalized energy attenuation and the corrected transmission time delay, comparing the feature matrix with the similarity of bubble feature modes in a preset mode library, and identifying the bubble event and estimating the volume if the similarity is larger than a preset threshold; and correcting the reference fat injection flow in real time, and deducting the flow corresponding to the estimated volume of the bubble event to obtain the real-time fat injection flow. Optionally, the calculating the wall adhesion history factor based on the fat injection intermittent duration and the estimated volume of the identified bubbles in the previous cycle, and determining the slip compensation coefficient based on the wall adhesion history factor includes: Weighting calculation is carried out on the fat injection intermittent time length and the estimated volume of the identified bubbles in the previous period to obtain a wall adhesion historical factor; and determini