A multi-parameter adaptive lubrication cooperative control method for high-speed sliding bearing

Abstract

This invention discloses a multi-parameter adaptive lubrication collaborative control method for high-speed sliding bearings, belonging to the field of high-speed sliding bearing lubrication control technology. The method includes the following steps: embedding a multi-source sensor group on the bearing to calibrate the collected oil film thickness, bearing surface temperature, and load; constructing adjustable execution units for oil supply flow rate, oil supply pressure, and oil supply temperature; synchronously collecting and preprocessing the calibrated oil film thickness, bearing surface temperature, and load at a fixed sampling frequency; establishing the coupling relationship between oil film thickness, lubricating oil viscosity, and bearing surface temperature; predicting the load change trend over a future set time period; constructing a multi-objective optimization function for oil film-temperature-load, dynamically allocating weights based on the bearing's current speed and load; solving the multi-objective optimization function; collecting the adjusted actual parameters and resubmitting them into the multi-objective optimization function for deviation verification. This invention achieves global collaborative optimization of oil film, temperature, and load using the above method.

Description

Technical Field

[0001] This invention relates to the technical field of lubrication control for high-speed sliding bearings, and in particular to a multi-parameter adaptive lubrication coordinated control method for high-speed sliding bearings. Background Technology

[0002] High-speed sliding bearings are core supporting components of various high-speed rotating equipment (such as machine tool spindles, steam turbines, and high-speed motors), and their lubrication condition directly determines the operating accuracy, stability, and service life of the equipment. Under high-speed, variable-load conditions, there is a strong coupling relationship between bearing oil film thickness, operating temperature, and load: excessively thin oil film thickness can easily lead to frictional wear between the journal and the bearing bush, and even bearing failure; excessively high temperature will reduce the viscosity of the lubricating oil, weaken the oil film's load-bearing capacity, and further exacerbate oil film thinning; sudden load changes will cause a sharp change in oil film pressure, triggering oil film oscillation and disrupting the stability of the lubrication system.

[0003] Existing high-speed sliding bearing lubrication control technologies mostly employ a single-parameter independent control mode, adjusting only the oil film thickness or temperature individually without considering the coupling relationship among these three factors. This results in low control accuracy, slow response, and difficulty in adapting to high-speed variable load conditions. Furthermore, the weight allocation of existing control methods is mostly a fixed value, unable to be dynamically adjusted according to changes in operating conditions such as speed and load. This leads to uneven control performance under different operating conditions, making it difficult to achieve global coordinated optimization of oil film, temperature, and load. Summary of the Invention

[0004] The purpose of this invention is to provide a multi-parameter adaptive lubrication coordinated control method for high-speed sliding bearings, which solves the problems of low accuracy, slow response, and poor adaptability of traditional control methods.

[0005] To achieve the above objectives, the present invention provides a multi-parameter adaptive lubrication coordinated control method for high-speed sliding bearings, comprising the following steps: S1. Embed a multi-source sensor group on the bearing to calibrate the collected oil film thickness, bearing surface temperature and load respectively; S2. A solenoid flow valve and an electro-hydraulic proportional relief valve are connected in series in the main oil circuit of the bearing lubrication system, and an oil temperature cooler is installed in the lubrication return oil circuit. These constitute adjustable actuators for oil supply flow, oil supply pressure and oil supply temperature, respectively. Each actuator is connected to the analog output port of the PLC controller. S3. Synchronously collect and preprocess the calibrated oil film thickness, tile surface temperature and load at a fixed sampling frequency; S4. Based on the Reynolds equation and the heat conduction equation, establish the coupling relationship between oil film thickness, lubricating oil viscosity, and bearing surface temperature; S5. Using historical load time series data of a preset duration as input, a lightweight LSTM model is used to predict the load change trend for a future set duration. S6. Construct a multi-objective optimization function for oil film-temperature-load, and dynamically allocate weights based on the current bearing speed and load; S7. Using oil film thickness deviation, temperature deviation, load deviation and corresponding deviation change rate as input, solve the multi-objective optimization function and output the oil supply pressure command, oil supply flow command and oil supply temperature command respectively to drive the electro-hydraulic proportional relief valve, electromagnetic flow valve and oil temperature cooler to operate synchronously. S8. Collect the actual parameters of oil film, temperature, and load after adjustment, and resubmit them into the multi-objective optimization function for deviation verification. When the oil film thickness is lower than the safety lower limit, the bearing surface temperature exceeds the temperature threshold, or the load changes beyond the allowable fluctuation range, trigger the emergency intervention strategy.

[0006] Preferably, in step S1, an integrated oil film-temperature sensor is embedded in the non-load-bearing area of ​​the high-speed sliding bearing bush. The integrated oil film-temperature sensor is embedded in the non-load-bearing area of ​​the bush and the detection end face is flush with the surface of the bush. The mounting hole is sealed and insulated with high-temperature resistant sealant. A piezoelectric load sensor is installed at the bottom of the bearing housing. The load sensor is padded between the bearing housing and the equipment base, and the force is uniform and without tilting. A Hall speed sensor is arranged at the shaft end.

[0007] Preferably, in step S3, the preprocessing involves extracting historical data from the last five moments for the oil film thickness, bearing surface temperature, and load at each acquisition moment, substituting these data into the filtering formula to calculate the filtered data, and determining whether the filtered data exceeds a preset range. If the filtered data exceeds the preset range, the filtered value from the previous moment is used as the replacement, and a slight alarm signal is issued simultaneously. The filtering formula is: ; ; ; in, For time, The sampling interval is... The length of the filter window. After filtering Oil film thickness at any given time After filtering The temperature of the tile surface at any given time, After filtering The load-bearing capacity at any time For the first Oil film thickness after calibration at any time. For the first The temperature of the tile surface after calibration at any time. For the first The load is calibrated at a certain time.

[0008] Preferably, step S4 specifically includes the following steps: S41. Establish the Reynolds equation for oil film lubrication: ; in, For oil film pressure, The dynamic viscosity of the lubricating oil. For the oil film axial coordinate, For the circumferential coordinates of the oil film, The relative sliding velocity between the bearing journal and the bearing pad surface in the axial direction. This refers to the relative sliding speed between the bearing journal and the bearing pad surface in the circumferential direction. S42. Establish the oil film heat conduction formula: ; in, For the density of lubricating oil, The specific heat capacity of lubricating oil at constant pressure. The thermal conductivity of the lubricating oil, The coordinates are in the radial thickness direction of the oil film. The velocity of the fluid within the oil film; S43, The viscosity of lubricating oil changes with temperature as follows: ; in, Reference temperature The viscosity of the lubricating oil is as follows: Viscosity-temperature coefficient; S44. Construct an oil film-temperature matching evaluation model: ; in, For matching degree, The oil film thickness is the baseline; if it exceeds the preset matching range, a linkage adjustment will be triggered.

[0009] Preferably, step S5 specifically includes the following steps: S51. Extract the filtered load data within the last 10 seconds and use it as the model input data; S52, the lightweight LSTM model has 100 nodes in the input layer, 16 nodes in the hidden layer, and 10 nodes in the output layer; S53, The model outputs the predicted load value within the next 1 second; S54. Calculate the prediction error using the following formula: ; in, To predict the load, the prediction is valid if the prediction error is no greater than 5%; otherwise, historical data from the past 15 seconds should be re-entered for a new prediction.

[0010] Preferably, in step S6, the oil film-temperature-load multi-objective optimization function is: ; in, To optimize the objective function value, the smaller the better. , and These are the weights for oil film thickness, temperature, and load, respectively, and their sum is 1. This represents the predicted load value.

[0011] Preferably, in step S6, the operating condition type is determined based on the current bearing speed and load, and the weights are dynamically adjusted, according to the following specific rules: when , At that time, it was a high-speed, light-load operating condition. , , ; when , At that time, it was a low-speed, heavy-load operating condition. , , ; when , At that time, in order to stabilize the working conditions, , 5, ; when At that time, it was an abnormal temperature condition. , , .

[0012] Preferably, in step S8, the adjusted deviation value is calculated: ; ; ; in, The adjusted oil film thickness, To adjust the temperature of the tile surface, If any deviation of the adjusted load exceeds the preset range, return to step S4 and perform the coupling analysis again.

[0013] Preferably, an emergency response plan is provided, with the following specific rules: when If the oil supply pressure is not increased to 0.8MPa, the bearing speed is reduced. If the oil film thickness does not recover to the minimum constraint thickness within 3 seconds, the lubrication system and bearing operation are stopped and an emergency alarm is issued. when If the temperature does not drop below the maximum constraint temperature within 5 seconds, immediately increase the cooling power of the oil cooler to the maximum and increase the oil supply flow. If the temperature does not drop below the maximum constraint temperature within 5 seconds, stop the bearing operation and issue an emergency alarm. when In such cases, the oil supply pressure and flow rate are quickly adjusted to adapt to sudden load changes, and the sudden data is recorded to facilitate subsequent fault analysis.

[0014] Therefore, the above-mentioned multi-parameter adaptive lubrication coordinated control method for high-speed sliding bearings, as described in this invention, has the following advantages: (1) In this invention, by establishing an oil film-temperature coupling analysis model, the mutual influence between the two is accurately quantified, avoiding system imbalance caused by single parameter adjustment, realizing coordinated and stable control of oil film-temperature-load, and greatly improving the reliability of bearing operation.

[0015] (2) In this invention, based on the real-time speed and load of the bearing, different working conditions such as high speed light load, low speed heavy load, stable working conditions, and abnormal temperature are automatically determined, and the control weights of oil film thickness, temperature and load are dynamically adjusted to ensure that global optimization control can be achieved under different working conditions.

[0016] (3) In this invention, the load prediction mechanism is combined to adapt to load changes in advance and solve the problem of traditional control lag.

[0017] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating a multi-parameter adaptive lubrication coordinated control method for high-speed sliding bearings according to the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Specific model specifications need to be selected and determined according to the actual specifications of the device, etc. The specific selection calculation method adopts existing technology in the art, and therefore will not be described in detail.

[0020] Example like Figure 1As shown, this invention provides a multi-parameter adaptive lubrication coordinated control method for high-speed sliding bearings, comprising the following steps: S1. Embed a multi-source sensor group on the bearing. Embed an integrated oil film-temperature sensor in the non-load-bearing area of ​​the high-speed sliding bearing bush. The integrated oil film-temperature sensor is embedded in the non-load-bearing area of ​​the bush and the detection end face is flush with the bush surface. The mounting hole is sealed and insulated with high-temperature resistant sealant. Install a piezoelectric load sensor at the bottom of the bearing housing. The load sensor is padded between the bearing housing and the equipment base. The force is uniform and there is no tilt. Arrange Hall speed sensors at the shaft end to calibrate the collected oil film thickness, bush surface temperature and load respectively. S2. A solenoid flow valve and an electro-hydraulic proportional relief valve are connected in series in the main oil circuit of the bearing lubrication system, and an oil temperature cooler is installed in the lubrication return oil circuit. These constitute adjustable actuators for oil supply flow, oil supply pressure and oil supply temperature, respectively. Each actuator is connected to the analog output port of the PLC controller. S3. Synchronously collect and preprocess the calibrated oil film thickness, bearing surface temperature, and load at a fixed sampling frequency. Preprocessing involves extracting historical data from the last five time points for each data collection moment, substituting these data into a filtering formula to calculate the filtered data, and determining whether the filtered data exceeds a preset range. If the filtered data exceeds the preset range, the filtered value from the previous moment is used as the replacement, and a slight alarm signal is issued. The filtering formula is: ; ; ; in, For time, The sampling interval is... The length of the filter window. After filtering Oil film thickness at any given time After filtering The temperature of the tile surface at any given time, After filtering The load-bearing capacity at any time For the first Oil film thickness after calibration at any time. For the first The temperature of the tile surface after calibration at any time. For the first The load is calibrated at a certain time.

[0021] S4. Based on the Reynolds equation and the heat conduction equation, establish the coupling relationship between oil film thickness, lubricating oil viscosity, and bearing surface temperature, specifically including the following steps: S41. Establish the Reynolds equation for oil film lubrication: ; in, For oil film pressure, The dynamic viscosity of the lubricating oil. For the oil film axial coordinate, For the circumferential coordinates of the oil film, The relative sliding velocity between the bearing journal and the bearing pad surface in the axial direction. This refers to the relative sliding speed between the bearing journal and the bearing pad surface in the circumferential direction. S42. Establish the oil film heat conduction formula: ; in, For the density of lubricating oil, The specific heat capacity of lubricating oil at constant pressure. The thermal conductivity of the lubricating oil, The coordinates are in the radial thickness direction of the oil film. The velocity of the fluid within the oil film; S43, The viscosity of lubricating oil changes with temperature as follows: ; in, Reference temperature The viscosity of the lubricating oil is as follows: Viscosity-temperature coefficient; S44. Construct an oil film-temperature matching evaluation model: ; in, For matching degree, The oil film thickness is the baseline; if it exceeds the preset matching range, a linkage adjustment will be triggered.

[0022] S5. Using historical load time-series data of a preset duration as input, a lightweight LSTM model is used to predict the load change trend for a future preset duration. This includes the following steps: S51. Extract the filtered load data within the last 10 seconds and use it as the model input data; S52, the lightweight LSTM model has 100 nodes in the input layer, 16 nodes in the hidden layer, and 10 nodes in the output layer; S53, The model outputs the predicted load value within the next 1 second; S54. Calculate the prediction error using the following formula: ; in, To predict the load, the prediction is valid if the prediction error is no greater than 5%; otherwise, historical data from the past 15 seconds should be re-entered for a new prediction.

[0023] S6. Construct a multi-objective optimization function for oil film-temperature-load. Based on the current bearing speed and load, dynamically allocate weights. The multi-objective optimization function for oil film-temperature-load is as follows: ; in, To optimize the objective function value, the smaller the better. , and These are the weights for oil film thickness, temperature, and load, respectively, and their sum is 1. This represents the predicted load value.

[0024] Based on the current bearing speed and load, the operating condition type is determined, and the weights are dynamically adjusted. The specific rules are as follows: when , At that time, it was a high-speed, light-load operating condition. , , ; when , At that time, it was a low-speed, heavy-load operating condition. , , ; when , At that time, in order to stabilize the working conditions, , 5, ; when At that time, it was an abnormal temperature condition. , , .

[0025] S7. Using oil film thickness deviation, temperature deviation, load deviation and corresponding deviation change rate as input, solve the multi-objective optimization function and output the oil supply pressure command, oil supply flow command and oil supply temperature command respectively to drive the electro-hydraulic proportional relief valve, electromagnetic flow valve and oil temperature cooler to operate synchronously. S8. Collect the actual parameters of oil film, temperature, and load after adjustment, and resubmit them into the multi-objective optimization function for deviation verification. When the oil film thickness is lower than the safety lower limit, the bearing surface temperature exceeds the temperature threshold, or the load changes beyond the allowable fluctuation range, trigger the emergency intervention strategy.

[0026] Calculate the adjusted deviation value: ; ; ; in, The adjusted oil film thickness, To adjust the temperature of the tile surface, If any deviation of the adjusted load exceeds the preset range, return to step S4 and perform the coupling analysis again.

[0027] An emergency response plan has been established, and the specific rules are as follows: when If the oil supply pressure is not increased to 0.8MPa, the bearing speed is reduced. If the oil film thickness does not recover to the minimum constraint thickness within 3 seconds, the lubrication system and bearing operation are stopped and an emergency alarm is issued. when If the temperature does not drop below the maximum constraint temperature within 5 seconds, immediately increase the cooling power of the oil cooler to the maximum and increase the oil supply flow. If the temperature does not drop below the maximum constraint temperature within 5 seconds, stop the bearing operation and issue an emergency alarm. when In such cases, the oil supply pressure and flow rate are quickly adjusted to adapt to sudden load changes, and the sudden data is recorded to facilitate subsequent fault analysis.

[0028] Therefore, this invention employs a multi-parameter adaptive lubrication coordinated control method for high-speed sliding bearings to achieve global coordinated optimization of oil film, temperature, and load, thereby improving the reliability and economy of high-speed sliding bearing operation.

[0029] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A multi-parameter adaptive lubrication coordinated control method for high-speed sliding bearings, characterized in that: Includes the following steps: S1. Embed a multi-source sensor group on the bearing to calibrate the collected oil film thickness, bearing surface temperature and load respectively; S2. A solenoid flow valve and an electro-hydraulic proportional relief valve are connected in series in the main oil circuit of the bearing lubrication system, and an oil temperature cooler is installed in the lubrication return oil circuit. These constitute adjustable actuators for oil supply flow, oil supply pressure and oil supply temperature, respectively. Each actuator is connected to the analog output port of the PLC controller. S3. Synchronously collect and preprocess the calibrated oil film thickness, tile surface temperature and load at a fixed sampling frequency; S4. Based on the Reynolds equation and the heat conduction equation, establish the coupling relationship between oil film thickness, lubricating oil viscosity, and bearing surface temperature; S5. Using historical load time series data of a preset duration as input, a lightweight LSTM model is used to predict the load change trend for a future set duration. S6. Construct a multi-objective optimization function for oil film-temperature-load, and dynamically allocate weights based on the current bearing speed and load; S7. Using oil film thickness deviation, temperature deviation, load deviation and corresponding deviation change rate as input, solve the multi-objective optimization function and output the oil supply pressure command, oil supply flow command and oil supply temperature command respectively to drive the electro-hydraulic proportional relief valve, electromagnetic flow valve and oil temperature cooler to operate synchronously. S8. Collect the actual parameters of oil film, temperature, and load after adjustment, and resubmit them into the multi-objective optimization function for deviation verification. When the oil film thickness is lower than the safety lower limit, the bearing surface temperature exceeds the temperature threshold, or the load changes beyond the allowable fluctuation range, trigger the emergency intervention strategy.

2. The multi-parameter adaptive lubrication coordinated control method for high-speed sliding bearings according to claim 1, characterized in that: In step S1, an integrated oil film-temperature sensor is embedded in the non-load-bearing area of ​​the high-speed sliding bearing bush. The integrated oil film-temperature sensor is embedded in the non-load-bearing area of ​​the bush and the detection end face is flush with the surface of the bush. The mounting hole is sealed and insulated with high-temperature resistant sealant. A piezoelectric load sensor is installed at the bottom of the bearing housing. The load sensor is padded between the bearing housing and the equipment base, and the force is uniform and without tilt. A Hall speed sensor is installed at the shaft end.

3. The multi-parameter adaptive lubrication coordinated control method for high-speed sliding bearings according to claim 2, characterized in that: In step S3, preprocessing involves extracting historical data from the last five moments for each data acquisition moment, including oil film thickness, bearing surface temperature, and load. This data is then substituted into a filtering formula to calculate the filtered data. The filtered data is then checked to determine if it exceeds a preset range. If it does, the filtered value from the previous moment is used instead, and a slight alarm signal is issued. The filtering formula is as follows: ； ； ； in, For time, The sampling interval is... The length of the filter window. After filtering Oil film thickness at any given time After filtering The temperature of the tile surface at any given time, After filtering The load-bearing capacity at any time For the first Oil film thickness after calibration at any time. For the first The temperature of the tile surface after calibration at any time. For the first The load is calibrated at a certain time.

4. The multi-parameter adaptive lubrication coordinated control method for high-speed sliding bearings according to claim 3, characterized in that: Step S4 Specifically, the following steps are included: S41. Establish the Reynolds equation for oil film lubrication: ； in, For oil film pressure, The dynamic viscosity of the lubricating oil. For the oil film axial coordinate, For the circumferential coordinates of the oil film, The relative sliding velocity between the bearing journal and the bearing pad surface in the axial direction. This refers to the relative sliding speed between the bearing journal and the bearing pad surface in the circumferential direction. S42. Establish the oil film heat conduction formula: ； in, For the density of lubricating oil, The specific heat capacity of lubricating oil at constant pressure. The thermal conductivity of the lubricating oil, The coordinates are in the radial thickness direction of the oil film. The velocity of the fluid within the oil film; S43, The viscosity of lubricating oil changes with temperature as follows: ； in, Reference temperature The viscosity of the lubricating oil is as follows: Viscosity-temperature coefficient; S44. Construct an oil film-temperature matching evaluation model: ； in, For matching degree, The oil film thickness is the baseline; if it exceeds the preset matching range, a linkage adjustment will be triggered.

5. The multi-parameter adaptive lubrication coordinated control method for high-speed sliding bearings according to claim 4, characterized in that: Step S5 specifically includes the following steps: S51. Extract the filtered load data within the last 10 seconds and use it as the model input data; S52, the lightweight LSTM model has 100 nodes in the input layer, 16 nodes in the hidden layer, and 10 nodes in the output layer; S53, The model outputs the predicted load value within the next 1 second; S54. Calculate the prediction error using the following formula: ； in, To predict the load, the prediction is valid if the prediction error is no greater than 5%; otherwise, historical data from the past 15 seconds should be re-entered for a new prediction.

6. The multi-parameter adaptive lubrication coordinated control method for high-speed sliding bearings according to claim 5, characterized in that: In step S6, the multi-objective optimization function for oil film-temperature-load is: ； in, To optimize the objective function value, the smaller the better. , and These are the weights for oil film thickness, temperature, and load, respectively, and their sum is 1. This represents the predicted load value.

7. The multi-parameter adaptive lubrication coordinated control method for high-speed sliding bearings according to claim 6, characterized in that: In step S6, the operating condition type is determined based on the current bearing speed and load, and the weights are dynamically adjusted according to the following rules: when , At that time, it was a high-speed, light-load operating condition. , , ; when , At that time, it was a low-speed, heavy-load operating condition. , , ; when , At that time, in order to stabilize the working conditions, , 5, ; when At that time, it was an abnormal temperature condition. , , .

8. The multi-parameter adaptive lubrication coordinated control method for high-speed sliding bearings according to claim 7, characterized in that: In step S8, the adjusted deviation value is calculated: ； ； ； in, The adjusted oil film thickness, To adjust the temperature of the tile surface, If any deviation of the adjusted load exceeds the preset range, return to step S4 and perform the coupling analysis again.

9. The multi-parameter adaptive lubrication coordinated control method for high-speed sliding bearings according to claim 8, characterized in that: An emergency response plan has been established, and the specific rules are as follows: when If the oil supply pressure is not increased to 0.8MPa, the bearing speed is reduced. If the oil film thickness does not recover to the minimum constraint thickness within 3 seconds, the lubrication system and bearing operation are stopped and an emergency alarm is issued. when If the temperature does not drop below the maximum constraint temperature within 5 seconds, immediately increase the cooling power of the oil cooler to the maximum and increase the oil supply flow. If the temperature does not drop below the maximum constraint temperature within 5 seconds, stop the bearing operation and issue an emergency alarm. when In such cases, the oil supply pressure and flow rate are quickly adjusted to adapt to sudden load changes, and the sudden data is recorded to facilitate subsequent fault analysis.

Images