CN115081127A - Method for calculating oil stirring loss of rotating part of comprehensive transmission device - Google Patents
Method for calculating oil stirring loss of rotating part of comprehensive transmission device Download PDFInfo
- Publication number
- CN115081127A CN115081127A CN202210450703.9A CN202210450703A CN115081127A CN 115081127 A CN115081127 A CN 115081127A CN 202210450703 A CN202210450703 A CN 202210450703A CN 115081127 A CN115081127 A CN 115081127A
- Authority
- CN
- China
- Prior art keywords
- oil
- basic unit
- loss
- stirring
- oil stirring
- 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
- 238000003756 stirring Methods 0.000 title claims abstract description 136
- 230000005540 biological transmission Effects 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000004364 calculation method Methods 0.000 claims abstract description 53
- 238000010801 machine learning Methods 0.000 claims abstract description 22
- 238000004088 simulation Methods 0.000 claims description 37
- 238000012360 testing method Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 239000007788 liquid Substances 0.000 claims description 8
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 239000012530 fluid Substances 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 abstract description 3
- 238000011160 research Methods 0.000 abstract description 3
- 238000012512 characterization method Methods 0.000 abstract description 2
- 238000012938 design process Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000017525 heat dissipation Effects 0.000 abstract description 2
- 238000005461 lubrication Methods 0.000 abstract description 2
- 238000005457 optimization Methods 0.000 abstract description 2
- 239000002699 waste material Substances 0.000 abstract description 2
- 239000003921 oil Substances 0.000 description 116
- 238000010586 diagram Methods 0.000 description 3
- 239000010687 lubricating oil Substances 0.000 description 3
- 238000012356 Product development Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 230000001050 lubricating effect Effects 0.000 description 1
- 230000009347 mechanical transmission Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Abstract
The invention provides a method for calculating the oil stirring loss of a rotating part of a comprehensive transmission device. Through the combination of the characterization parameters of the rotary oil stirring base unit and the typical working conditions with machine learning, the rapid calculation of the oil stirring loss of various rotating parts of the comprehensive transmission device can be realized, the influence rule is obtained, the mathematical model only containing a small amount of characteristic parameters is finally fitted, a large amount of calculation time can be saved, the research progress of the engineering technology is greatly promoted, and the rapid calculation method can be directly used for rapid solution in the engineering design process. Through the accurate calculation of the oil stirring loss, a foundation can be laid for the follow-up product structure optimization, lubrication and heat dissipation cooperative control, the energy waste is reduced, and the long-distance rushing capacity of the armored tracked vehicle is enhanced.
Description
Technical Field
The invention belongs to the technical field of performance analysis calculation and evaluation, and particularly relates to a method for calculating the oil stirring loss of a rotating part of a comprehensive transmission device.
Background
The comprehensive transmission device belongs to a complex mechanical transmission device, and comprises key parts such as a torque converter, a gear, a shaft, a bearing and the like, wherein the power loss of the comprehensive transmission device comprises the oil stirring loss of a rotating part, the friction loss of gear transmission, the power loss of a lubricating system and the like. Through comparison of test results, the proportion of the idle loss power under the mechanical working condition in the power loss of the whole comprehensive transmission device reaches 80-90%, and the oil stirring loss of the rotating piece accounts for 70-90% of the idle loss power of the comprehensive transmission device. Therefore, there is a need to focus on reducing rotating member churning losses to improve driveline efficiency.
In order to improve the power density, rotating parts such as a bearing, a shaft, a gear, a hydraulic torque converter and the like in the integrated transmission device are generally designed to have a smaller distance with adjacent parts, lubricating oil is difficult to discharge in time in the integrated transmission device due to a small surrounding installation space, and oil stirring power loss generated by stirring the lubricating oil is generated in the rotating process of the rotating parts, so that not only are the mechanical energy influence and the transmission efficiency wasted, but also the oil stirring power loss is almost completely converted into heat, so that the internal temperature of the transmission device is increased, the service life and the reliability of rubber sealing parts, electric parts and the like are seriously influenced, and a serious heat radiation burden is brought to a thermal management system of a vehicle. Therefore, reducing the churning loss of the rotating part of the comprehensive transmission device is one of important ways and design points for improving efficiency and reliability, and accurately predicting the churning power loss is the premise and the basis for reducing the churning loss.
The rotating part of the comprehensive transmission device has a complex structure shape, a complex structure shape of an operating environment, various gaps and different flow states of a flow field, and relates to the technical fields of structure dynamics, hydrodynamics, thermodynamics, numerical simulation and the like. In order to obtain an accurate oil churning loss prediction result, in the prior art, computational fluid dynamics software is usually adopted to directly perform modeling simulation on a researched rotating part, an orthogonal table needs to be established to calculate a plurality of single working conditions, then interpolation solving is performed through a fitting method, the calculation is long in time consumption, and the research progress is difficult to guarantee.
Aiming at the oil stirring loss calculation of the comprehensive transmission device, multiple working condition factors such as rotating speed, working temperature, lubricating oil liquid level height, different shapes and sizes need to be considered, meanwhile, the installation space of a rotating part also needs to be considered, and the factors can be involved in the design of an actual product. Therefore, the number of simulation calculation models and the number of working conditions are huge, and in a limited product development period, the aspects of the performance of simulation software, the simulation models, the setting of simulation step length and grid size and the like need to be comprehensively selected, but the huge calculation amount still causes that the calculation method is difficult to apply in the complex product development process.
Disclosure of Invention
Technical problem to be solved
The invention provides a method for calculating the oil stirring loss of a rotating part of a comprehensive transmission device, which aims to solve the technical problems of long calculation time and difficult engineering application of the traditional method for calculating the oil stirring loss of the rotating part by performing heat, flow and solid coupling on the basis of computational fluid mechanics software.
(II) technical scheme
In order to solve the technical problem, the invention provides an oil stirring loss calculation method for a rotating part of a comprehensive transmission device, which comprises the following steps:
s1, normalizing basic units in different shapes by a comprehensive transmission device rotating member formed by overlapping a plurality of rotary oil stirring basic units in different shapes and sizes, enabling each basic unit to be equivalent to the integral of a thin-wall disc with a corresponding diameter respectively, representing by adopting two parameters of the length L and the diameter D of the thin-wall disc, and dividing the normalized rotary oil stirring basic unit into three decomposition surfaces, namely a left end surface, a cylindrical surface and a right end surface;
firstly, modeling 1 basic unit by computational fluid dynamics software and calculating the oil churning loss; the oil stirring loss calculation process of each decomposition surface of 1 basic unit comprises the steps of obtaining oil stirring loss of 2 basic units in seamless connection through simulation, subtracting the oil stirring loss of 1 basic unit obtained through simulation under the same working condition to obtain the oil stirring loss of a cylindrical surface with the length of L, and subtracting the oil stirring loss of the cylindrical surface of the basic unit from the oil stirring loss of 1 basic unit to obtain the oil stirring loss of 2 end surfaces of the oil stirring basic unit; dividing the oil stirring loss of 2 end faces of the obtained oil stirring basic unit by 2 to obtain the oil stirring loss of a single end face of the basic unit; substituting the calculated oil stirring loss of the single end face of the oil stirring basic unit into the calculation, and subtracting the oil stirring loss of 2 end faces in the basic unit from the oil stirring loss of 1 basic unit to obtain the oil stirring loss of the cylindrical surface of the oil stirring basic unit;
s2, using the test testing device of the rotary stirring oil base unit, respectively acquiring the stirring oil liquid level height H, the operating temperature T, the rotating speed v and the stirring oil torque TN of the rotary stirring oil base unit through the oil level gauge, the temperature sensor, the angular velocity sensor and the torque sensor of the motor, and calculating the stirring oil power loss of the rotary stirring oil base unit according to the following formula:
in the formula, P is the oil stirring loss in kW; TN is the stirring torque, unit N.m; v is the rotating speed of the rotary stirring base unit in m/s;
s3, verifying the simulation result of the oil churning loss of the basic unit for training the machine learning algorithm through the test in S2, and utilizing the relative error
Judging whether the simulation result of the oil stirring loss of the basic unit meets the engineering requirement, wherein y is a test value of the oil stirring power loss of the basic unit;
the method is a simulation value of the oil stirring power loss of a basic unit;
if the relative error RE is more than 20%, the oil mixing power loss simulation model of the basic unit is not established, the height L and the diameter D of the basic unit for training the machine learning algorithm need to be adjusted again, and iterative updating is carried out until the relative error is controlled within 20%;
if the relative error between the simulation result of the oil mixing power loss of the basic unit and the test result of the oil mixing power loss of the basic unit is controlled within 20 percent, designing orthogonal calculation tables of various working conditions, wherein the orthogonal calculation tables comprise 5 influencing factors, namely the height L and the diameter D of the basic unit for training, the height H of the oil mixing liquid level, the operating temperature T and the rotating speed v, and different values n are designed according to actual requirements according to the levels of the factors 1 、n 2 、n 3 、n 4 、n 5 Finally, obtaining the oil stirring torque TN of the basic unit under each working condition through a simulation model;
s4, taking the influence factors in the orthogonal calculation table as input, taking the oil stirring torque TN obtained through the simulation model established in the S1 as output, substituting the output into machine learning for training, and selecting the machine learning algorithm according to the number of actual samples; according to an orthogonal scheme shown in an orthogonal calculation table, if the sample size of the simulation calculation of the oil churning loss of the basic unit, namely the corresponding test number, is less than or equal to 50, a support vector machine is selected for training; if the sample size of the simulation calculation of the oil churning loss of the basic unit is more than 50, training by adopting a neural network; and then extrapolating the calculation results of the rotary stirring basic unit under various working conditions by a machine learning method to obtain the oil stirring loss result of the rotary basic unit of the rotary part to be detected consisting of the basic units under the corresponding working conditions.
(III) advantageous effects
The invention provides a method for calculating the oil stirring loss of a rotating part of a comprehensive transmission device. Through the combination of the characterization parameters of the rotary oil stirring base unit and the typical working conditions with machine learning, the rapid calculation of the oil stirring loss of various rotating parts of the comprehensive transmission device can be realized (the machine learning rapidly realizes interpolation and extrapolation, and the solving time of the finally formed mathematical model is not longer than 1 minute and is far lower than that of the traditional algorithm by 8 hours), the influence rule is obtained, the mathematical model only containing a small amount of characteristic parameters is finally fitted, a large amount of calculating time can be saved, the research progress of the engineering technology is greatly promoted, and the method can be directly used for rapid solution in the engineering design process. Through accurate calculation of oil stirring loss, a foundation can be laid for subsequent product structure optimization, lubrication and heat dissipation cooperative control, energy waste is further reduced, and the long-distance rushing capacity of the armored tracked vehicle is enhanced.
Drawings
FIG. 1 is a flow chart of a method for calculating churning loss of a rotating member according to an embodiment of the present invention;
FIG. 2 is an exploded view of the rotary stirring body unit in the embodiment of the invention;
FIG. 3a is a schematic diagram illustrating calculation of the oil churning loss at the end face of the rotary oil churning unit according to the embodiment of the present invention, and FIG. 3b is a schematic diagram illustrating calculation of the oil churning loss at the cylindrical surface;
FIG. 4 is a schematic view of a churning loss test bed for a key rotating member of the hydraulic mechanical integrated transmission device in the embodiment of the invention;
FIG. 5a is a flow chart of calculation of oil stirring loss of a key cylindrical rotating member based on superposition of basic units in the embodiment of the invention, and FIG. 5b is a flow chart of calculation of oil stirring loss of a key conical rotating member based on superposition of basic units in the embodiment of the invention;
FIG. 6 is a schematic diagram of the churning loss of different types of rotating members in an embodiment of the present invention.
Detailed Description
In order to make the objects, contents and advantages of the present invention clearer, the following detailed description of the embodiments of the present invention will be made in conjunction with the accompanying drawings and examples.
The embodiment provides a method for calculating the oil stirring loss of a rotating part of an integrated transmission device, the main flow of which is shown in fig. 1, and the method mainly comprises the following steps:
s1, for a comprehensive transmission device rotating piece formed by overlapping a plurality of rotary stirring oil basic units with different shapes and sizes, in order to calculate the oil stirring loss of the rotating piece by linearly overlapping the oil stirring loss of each basic unit, normalization processing is carried out on the basic units with different shapes such as a cylinder, a round table, a cone and the like, each basic unit is equivalent to the integral of a thin-wall disc with corresponding diameter, two parameters of the length L of the thin-wall disc and the diameter D of the thin-wall disc are adopted for representing, and the normalized rotary stirring oil basic units are divided into three decomposition surfaces of a left end surface, a cylindrical surface and a right end surface, as shown in figure 2.
First 1 elementary cell (length L, diameter D) was modeled by computational fluid dynamics software and the churning loss was calculated. The oil churning loss calculation process for each of the decomposition surfaces of 1 basic unit is shown in FIG. 3. As shown in fig. 3a, the oil churning loss of the seamless connection of 2 basic units is obtained through simulation, and the oil churning loss of 1 basic unit obtained through simulation under the same working condition is subtracted, so that the oil churning loss of the cylindrical surface with the length of L is obtained. Then, the oil stirring loss of the cylindrical surface of the basic unit (already marked in figure 1) is subtracted from the oil stirring loss of 1 basic unit, so that the oil stirring loss of 2 end surfaces of the oil stirring basic unit can be obtained. The oil churning loss of the single end face of the basic unit of the obtained churning oil can be obtained by dividing the oil churning loss of the 2 end faces of the basic unit of the obtained churning oil by 2. As shown in fig. 3b, the calculated oil stirring loss of a single end face of the oil stirring basic unit is substituted into the calculation, and the oil stirring loss of 2 end faces in the basic unit is subtracted from the oil stirring loss of 1 basic unit, so that the oil stirring loss of the cylindrical surface of the oil stirring basic unit can be obtained.
S2, using the test testing device of the rotary oil stirring basic unit shown in the figure 4, respectively acquiring the oil stirring liquid level height H, the operating temperature T, the rotating speed v and the oil stirring torque TN of the rotary oil stirring basic unit through an oil liquid height meter, a temperature sensor, an angular velocity sensor and a torque sensor which are arranged on a motor, and calculating the oil stirring power loss of the rotary oil stirring basic unit according to the following formula:
in the formula, P is the oil stirring loss in kW; TN is the stirring torque, unit N.m; v is the rotation speed of the rotary stirring basic unit in m/s.
S3, verifying the simulation result of the oil churning loss of the basic unit for training the machine learning algorithm in the flow chart of the figure 1 through the test in S2, and utilizing the relative error
Judging whether the simulation result of the oil stirring loss of the basic unit meets the engineering requirement, wherein y is a test value of the oil stirring power loss of the basic unit;
the method is a simulated value of the oil stirring power loss of the basic unit.
If the relative error RE is larger than 20%, the oil mixing power loss simulation model of the basic unit is not established, the height L and the diameter D of the basic unit for training the machine learning algorithm need to be readjusted, and iterative updating is carried out until the relative error is controlled within 20%.
Simulation result if oil stirring power loss of basic unit is equal toAnd (3) controlling the relative error of the oil stirring power loss test result of the basic unit within 20%, and designing orthogonal calculation tables of various working conditions, wherein the orthogonal calculation tables are shown in table 1. The orthogonal calculation table comprises 5 influencing factors, namely the height L and the diameter D of a basic unit for training, the height H of the oil stirring liquid level, the operating temperature T and the rotating speed v, wherein different values n can be designed according to actual requirements for the levels of the factors 1 、n 2 、n 3 、n 4 、n 5 And finally obtaining the oil stirring torque TN of the basic unit under each working condition through a simulation model. The orthogonal table can be extended with more factors and factor levels.
TABLE 1 orthogonal calculation table for training basic unit oil churning loss influence factors of machine learning algorithm
And S4, taking the influence factors in the table 1 as input, taking the oil stirring torque TN obtained through the simulation model established in the S1 as output, substituting the output into machine learning for training, wherein the machine learning algorithm can be selected according to the number of actual samples. According to the orthogonal scheme shown in table 1, if the sample size calculated by the simulation of the churning loss of the basic unit, namely the corresponding test number, is less than or equal to 50, a support vector machine is selected for training. And if the sample size of the simulation calculation of the oil churning loss of the basic unit is more than 50, training by using a neural network. And then extrapolating the calculation results of the rotary stirring basic unit under various working conditions by a machine learning method to obtain the oil stirring loss result of the rotary basic unit of the rotary part to be detected consisting of the basic units under the corresponding working conditions.
The above method is explained by taking the following calculation of the churning loss of two rotating members of a cylinder and a cone as an integral example.
As shown in FIG. 5a, taking the calculation of the oil churning loss of the cylinder as an example, the cylinder is decomposed into m basic units with the height l and the equal diameter D, wherein the sum of the heights of the m basic units with the height l is the height of the cylinder, and the diameter of the basic unit is equal to the diameter of the cylinder. Substituting the basic unit decomposed by the cylinder and the corresponding working condition into a machine learning algorithm to obtain the oil stirring loss of the basic unit, then obtaining the oil stirring loss of the end surface and the cylindrical surface of the basic unit by the calculation method in the figure 3, and finally carrying out integral summation to obtain the oil stirring loss of the cylinder.
Further calculations of cone churning losses are made to extend the versatility of the proposed method. As shown in fig. 5b, the cone is broken down into several heights l and n different diameters d 1 ，d 2 ，…，d n Wherein the sum of the heights of the n basic units with the height of l is the height of the cone, and the diameter of the basic units needs to be continuously changed according to the contour line of the cone. And substituting the basic unit decomposed by the cone and the corresponding working condition into a machine learning algorithm to obtain the oil stirring loss of the basic unit, then obtaining the oil stirring loss of the end surface and the conical surface of the basic unit by the calculation method in the figure 3, and finally carrying out integral summation to obtain the oil stirring loss of the cone.
The present method is demonstrated by the example in fig. 5 to enable churning loss calculations for cones, cones and other types of rotating parts. Firstly, a rotating member to be calculated, such as a cone or a cone, is decomposed into n basic units with different diameters and the same length. Then the churning loss of the decomposed n basic units is obtained according to the machine learning in S3. And then, the integral summation is carried out on the basic units with different diameters and the same length, so that the oil stirring power loss of the continuous rotating body can be obtained. Further, the different rotating bodies are arranged and combined again to obtain the oil stirring loss of the different types of rotating member combinations under the specified working condition, as shown in fig. 6.
As can be seen from the calculation examples of FIG. 5 and FIG. 6, the method provided by the invention can realize the calculation of the oil churning loss of different types of rotating members through the calculation of the oil churning loss of the basic unit and the integral summation, and the method has universality and convenience.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (1)
1. A method for calculating the oil stirring loss of a rotating part of an integrated transmission device is characterized by comprising the following steps of:
s1, normalizing basic units in different shapes by a comprehensive transmission device rotating member formed by overlapping a plurality of rotary oil stirring basic units in different shapes and sizes, enabling each basic unit to be equivalent to the integral of a thin-wall disc with a corresponding diameter respectively, representing by adopting two parameters of the length L and the diameter D of the thin-wall disc, and dividing the normalized rotary oil stirring basic unit into three decomposition surfaces, namely a left end surface, a cylindrical surface and a right end surface;
firstly, modeling 1 basic unit by computational fluid dynamics software and calculating the oil churning loss; the oil stirring loss calculation process of each decomposition surface of 1 basic unit comprises the steps of obtaining oil stirring loss of 2 basic units in seamless connection through simulation, subtracting the oil stirring loss of 1 basic unit obtained through simulation under the same working condition to obtain the oil stirring loss of a cylindrical surface with the length of L, and subtracting the oil stirring loss of the cylindrical surface of the basic unit from the oil stirring loss of 1 basic unit to obtain the oil stirring loss of 2 end surfaces of the oil stirring basic unit; dividing the oil stirring loss of 2 end faces of the obtained oil stirring basic unit by 2 to obtain the oil stirring loss of a single end face of the basic unit; substituting the calculated oil stirring loss of the single end face of the oil stirring basic unit into the calculation, and subtracting the oil stirring loss of 2 end faces in the basic unit from the oil stirring loss of 1 basic unit to obtain the oil stirring loss of the cylindrical surface of the oil stirring basic unit;
s2, using the test testing device of the rotary stirring oil base unit, respectively acquiring the stirring oil liquid level height H, the operating temperature T, the rotating speed v and the stirring oil torque TN of the rotary stirring oil base unit through the oil level gauge, the temperature sensor, the angular velocity sensor and the torque sensor of the motor, and calculating the stirring oil power loss of the rotary stirring oil base unit according to the following formula:
wherein, P is the oil stirring loss in kW; TN is the stirring torque, unit N.m; v is the rotating speed of the rotary stirring base unit in m/s;
s3, verifying the simulation result of the oil churning loss of the basic unit for training the machine learning algorithm through the test in S2, and utilizing the relative error
Judging whether the simulation result of the oil stirring loss of the basic unit meets the engineering requirement, wherein y is a test value of the oil stirring power loss of the basic unit;
the method is a simulation value of the oil stirring power loss of a basic unit;
if the relative error RE is more than 20%, the oil mixing power loss simulation model of the basic unit is not established, the height L and the diameter D of the basic unit for training the machine learning algorithm need to be adjusted again, and iterative updating is carried out until the relative error is controlled within 20%;
if the relative error between the simulation result of the oil mixing power loss of the basic unit and the test result of the oil mixing power loss of the basic unit is controlled within 20 percent, designing orthogonal calculation tables of various working conditions, wherein the orthogonal calculation tables comprise 5 influencing factors, namely the height L and the diameter D of the basic unit for training, the height H of the oil mixing liquid level, the operating temperature T and the rotating speed v, and different values n are designed according to actual requirements according to the levels of the factors 1 、n 2 、n 3 、n 4 、n 5 Finally, obtaining the oil stirring torque TN of the basic unit under each working condition through a simulation model;
s4, taking the influence factors in the orthogonal calculation table as input, taking the oil stirring torque TN obtained through the simulation model established in the S1 as output, substituting the output into machine learning for training, and selecting the machine learning algorithm according to the number of actual samples; according to an orthogonal scheme shown in an orthogonal calculation table, if the sample size of the simulation calculation of the oil churning loss of the basic unit, namely the corresponding test number, is less than or equal to 50, a support vector machine is selected for training; if the sample size of the simulation calculation of the oil churning loss of the basic unit is more than 50, training by adopting a neural network; and then extrapolating the calculation results of the rotary stirring basic unit under various working conditions by a machine learning method to obtain the oil stirring loss result of the rotary basic unit of the rotary part to be detected consisting of the basic units under the corresponding working conditions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210450703.9A CN115081127B (en) | 2022-04-26 | 2022-04-26 | Calculation method for oil stirring loss of rotating part of comprehensive transmission device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210450703.9A CN115081127B (en) | 2022-04-26 | 2022-04-26 | Calculation method for oil stirring loss of rotating part of comprehensive transmission device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115081127A true CN115081127A (en) | 2022-09-20 |
| CN115081127B CN115081127B (en) | 2024-04-09 |
Family
ID=83246917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210450703.9A Active CN115081127B (en) | 2022-04-26 | 2022-04-26 | Calculation method for oil stirring loss of rotating part of comprehensive transmission device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115081127B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105181332A (en) * | 2015-11-02 | 2015-12-23 | 盐城工学院 | Composite gear churning experiment device and method |
| CN108319737A (en) * | 2017-01-17 | 2018-07-24 | 沈阳工业大学 | The Flow and Temperature coupling Simulation analysis method of bullet train aluminum alloy gear case |
| WO2019242389A1 (en) * | 2018-06-21 | 2019-12-26 | 青岛迈金智能科技有限公司 | Riding table compensation algorithm based on relative sliding of multi-groove belts |
| CN112460241A (en) * | 2020-09-29 | 2021-03-09 | 中国北方车辆研究所 | Design method for inhibiting oil mixing power loss of transmission system |
| WO2021238762A1 (en) * | 2020-05-25 | 2021-12-02 | 精进电动科技股份有限公司 | Hybrid cooling motor |
| CN114295371A (en) * | 2021-11-23 | 2022-04-08 | 中国北方车辆研究所 | Comprehensive evaluation method for straight driving efficiency performance of hydraulic mechanical comprehensive transmission device |
-
2022
- 2022-04-26 CN CN202210450703.9A patent/CN115081127B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105181332A (en) * | 2015-11-02 | 2015-12-23 | 盐城工学院 | Composite gear churning experiment device and method |
| CN108319737A (en) * | 2017-01-17 | 2018-07-24 | 沈阳工业大学 | The Flow and Temperature coupling Simulation analysis method of bullet train aluminum alloy gear case |
| WO2019242389A1 (en) * | 2018-06-21 | 2019-12-26 | 青岛迈金智能科技有限公司 | Riding table compensation algorithm based on relative sliding of multi-groove belts |
| WO2021238762A1 (en) * | 2020-05-25 | 2021-12-02 | 精进电动科技股份有限公司 | Hybrid cooling motor |
| CN112460241A (en) * | 2020-09-29 | 2021-03-09 | 中国北方车辆研究所 | Design method for inhibiting oil mixing power loss of transmission system |
| CN114295371A (en) * | 2021-11-23 | 2022-04-08 | 中国北方车辆研究所 | Comprehensive evaluation method for straight driving efficiency performance of hydraulic mechanical comprehensive transmission device |
Non-Patent Citations (2)
| Title |
|---|
| 李晏;皮彪;王叶枫;刘林晶;陈辛波;: "基于移动粒子半隐式法的齿轮搅油损失分析与试验验证", 同济大学学报(自然科学版), no. 03, 15 March 2018 (2018-03-15), pages 92 - 96 * |
| 苏永红;张庆慧;: "变速箱中搅油功率损失的CFD分析", 机械工程与自动化, no. 04, 15 August 2020 (2020-08-15), pages 36 - 37 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115081127B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102658499B (en) | Spindle thermal distortion compensation method for precision horizontal machining center | |
| CN112784361B (en) | Method for optimizing structure of automobile engine compartment heat dissipation system based on proxy model | |
| CN108875213B (en) | Reactor core thermal hydraulic multi-scale analysis method | |
| CN111967107B (en) | NURBS (non-uniform rational B-spline) isogeometric solving method for oil film pressure field of internal feedback dynamic and static pressure sliding bearing | |
| Li et al. | Modeling and multi-objective optimization of cutting parameters in the high-speed milling using RSM and improved TLBO algorithm | |
| CN110889178A (en) | Method for predicting service life of flexible gear of harmonic reducer | |
| CN112733294B (en) | Design method of engine cylinder gasket | |
| CN112434452A (en) | Method and system equipment for determining shaft diameter fit tolerance of high-speed electric main shaft bearing | |
| Liu et al. | Thermal error modeling of gear hobbing machine based on IGWO-GRNN | |
| Chen et al. | Prediction and optimization of lubrication performance for a transfer case based on computational fluid dynamics | |
| CN115081127A (en) | Method for calculating oil stirring loss of rotating part of comprehensive transmission device | |
| Xu et al. | Optimal design and experimental research of the anti-cavitation structure in the water hydraulic relief valve | |
| Mo et al. | Statistical analysis of surface texture performance with provisions with uncertainty in texture dimensions | |
| Xin et al. | A multi-objective optimization design approach of large mining planetary gear reducer | |
| Liu et al. | Bionic optimization design for a CNC turntable based on thermal–mechanical coupling effect | |
| CN105095536B (en) | A kind of static pressure oil pad flow field characteristic numerical value emulation method considering surface topography | |
| Li et al. | Influence of piston number on churning losses in axial piston pumps | |
| Dhote et al. | Wear material determination and parameters optimization of an external gear pump by Taguchi technique | |
| Gong et al. | Numerical investigation on churning loss torque and oil distribution of reducer based on lattice boltzmann method | |
| Wang et al. | Temperature characteristics analysis of axial piston pump port plate pair | |
| CN114925558A (en) | Digital twinning modeling method for bearing test bed | |
| Zhang et al. | Prediction mathematic model and influencing factors of contact stress of cylindrical gear with arc tooth | |
| Zhu et al. | Heat characteristics analysis of electro-hydraulic servo valve | |
| CN109214128B (en) | Wet friction pair sliding friction process lubrication flow field distribution characteristic modeling method | |
| CN113704907A (en) | Gear contact fatigue life prediction method based on tooth surface stress field |
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 |