CN109598031B - Method and device for determining thickness of grease lubricating film - Google Patents
Method and device for determining thickness of grease lubricating film Download PDFInfo
- Publication number
- CN109598031B CN109598031B CN201811354644.5A CN201811354644A CN109598031B CN 109598031 B CN109598031 B CN 109598031B CN 201811354644 A CN201811354644 A CN 201811354644A CN 109598031 B CN109598031 B CN 109598031B
- Authority
- CN
- China
- Prior art keywords
- value
- film thickness
- neural network
- values
- network model
- 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.)
- Active
Links
Images
Classifications
-
- 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
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Abstract
The invention discloses a method and a device for determining the thickness of a grease lubricating film, wherein the method comprises the following steps: determining film thickness values under a plurality of groups of different input parameters according to a numerical simulation algorithm; training the neural network model by utilizing a plurality of groups of input values and corresponding film thickness values to obtain the trained neural network model, wherein the input values at least comprise an input load value, a entrainment speed value, a surface roughness value, a material parameter value and a hardness value; inputting the obtained current input load value, the entrainment speed value, the surface roughness value, the material parameter value and the hardness value into the trained neural network model to obtain a film thickness value; and outputting the film thickness value.
Description
Technical Field
The invention relates to the technical field of grease lubrication, in particular to a method and a device for determining thickness of a grease lubricating film.
Background
Currently, about 80% of part damage is caused by wear. The reduction of friction and wear is always the direction and the target of the research of scholars at home and abroad. One effective way to reduce friction and wear is lubrication.
Grease lubrication is widely applied to various rolling bearings and mechanical equipment due to good lubrication durability and sealing performance, especially under severe working conditions of high and low temperature, extreme pressure, corrosion, humidity and the like.
In the study of lubrication behavior of lubricants, the lubrication mechanism has become a major subject of investigation. And the judgment of the lubrication mechanism is generally determined by the ratio of the thickness of the grease lubricant film to the surface roughness of the friction pair. When the ratio of the thickness of the grease lubrication film to the surface roughness of the friction pair is 1-3, the lubrication mechanism is mixed lubrication. And boundary lubrication is performed when the ratio of the thickness of the grease lubrication film to the surface roughness of the friction pair is less than 1. And when the ratio of the thickness of the grease lubrication film to the surface roughness of the friction pair is more than 3, the grease lubrication is full-film lubrication. When the lubrication is full film lubrication, since the grease blocks direct contact of the friction pair material, wear is less likely to occur, and the lubrication state at this time is the optimum lubrication state.
In determining the lubrication mechanism, the film thickness is a critical factor in the determination. The film thickness is influenced by many factors, on one hand, from the lubricant itself, such as the viscosity and rheological properties of the lubricant; the characteristics of the friction pair material, such as roughness of the surface of the material, elastic modulus, hardness and the like of the material; and thirdly, external working condition conditions such as load, relative movement rate and the like.
At present, the film thickness under different parameters is measured by adopting an experimental means and instruments and equipment, and the measurement operation is complex.
Therefore, it is necessary to provide a new technical solution, which is improved in view of the above technical problems in the prior art.
Disclosure of Invention
An object of the present invention is to provide a new technical solution for detecting the thickness of a grease lubricant film.
According to a first aspect of the present invention, there is provided a method of determining a grease lubricant film thickness, comprising:
determining film thickness values under a plurality of groups of different input parameters according to a numerical simulation algorithm;
training the neural network model by utilizing a plurality of groups of input values and corresponding film thickness values to obtain the trained neural network model, wherein the input values at least comprise an input load value, a entrainment speed value, a surface roughness value, a material parameter value and a hardness value;
inputting the obtained current input load value, the entrainment speed value, the surface roughness value, the material parameter value and the hardness value into the trained neural network model to obtain a film thickness value;
and outputting the film thickness value.
Optionally, determining film thickness values under multiple groups of different input parameters according to a numerical simulation algorithm includes:
s1, obtaining a first film thickness value by using the obtained initial input load value and a film thickness equation;
s2, obtaining a lubricating grease fluid pressure value by using the first film thickness value and a Reynolds equation, and obtaining a microprotrusion contact pressure value by using the first film thickness value and a microprotrusion contact stress model equation;
s3, obtaining an input load value by using the lubricating grease fluid pressure value, the microprotrusion contact pressure value and a load balance equation;
and S4, performing iteration processing according to S1, S2 and S3 until the difference value of the fluid pressure values of the lubricating grease before and after the iteration, the difference value of the contact pressure values of the microprotrusions before and after the iteration and the difference value of the input load values before and after the iteration are all smaller than the preset difference value, and taking the film thickness value obtained by the iteration processing as the film thickness value corresponding to the initial input load value.
Optionally, obtaining a film thickness value by using the obtained initial input load value and a film thickness equation comprises:
acquiring an initial minimum contact clearance value of the contact surface of the friction pair;
and inputting the initial minimum contact gap value and the initial input load value into the film thickness equation to obtain a film thickness value.
Optionally, obtaining a grease fluid pressure value using the first film thickness value and a reynolds equation includes:
obtaining a rheological index value of the grease, an initial density value of the grease, an initial viscosity value of the grease, a surface roughness value of a contact surface of a friction pair and a value of a entrainment rate;
and inputting the first film thickness value, the rheological index value of the lubricating grease, the initial density value of the lubricating grease, the initial viscosity value of the lubricating grease, the surface roughness value of the contact surface of the friction pair and the entrainment rate value into the Reynolds equation to obtain the fluid pressure value of the lubricating grease.
Optionally, obtaining a microprotrusion contact pressure value using the first film thickness value and a microprotrusion contact stress model equation includes:
obtaining a surface parameter value of the friction pair, an elastic modulus value of the friction pair, a curvature radius value of the microprotrusions, a height value of the microprotrusions, an average gap value of a contact surface of the friction pair, a difference value of the average height of the microprotrusions and the average height of the surface and a hardness value of the friction pair;
and inputting the first film thickness value, the surface parameter value, the elastic modulus value of the friction pair, the curvature radius value of the microprotrusion, the height value of the microprotrusion, the average gap value of the contact surface of the friction pair, the difference value between the average height of the microprotrusion and the average height of the surface and the hardness value into a microprotrusion contact stress model equation to obtain a microprotrusion contact pressure value.
Optionally, training the neural network model by using a plurality of sets of input values and corresponding film thickness values to obtain a trained neural network model, including:
inputting the multiple groups of input values and the corresponding film thickness values into a neural network model;
optimizing the weight and the threshold of the neural network model by using a genetic algorithm;
and transmitting the corresponding weight and threshold value when the difference value between the predicted film thickness value output from the neural network model and the input film thickness value meets the training precision requirement to the neural network model to obtain the trained neural network model.
According to a second aspect of the present invention, there is provided a grease lubricant film thickness determination apparatus comprising:
the numerical simulation calculation module is used for determining film thickness values under a plurality of groups of different input parameters according to a numerical simulation algorithm;
the neural network training module is used for training the neural network model by utilizing a plurality of groups of input values and corresponding film thickness values to obtain the trained neural network model, wherein the input values at least comprise an input load value, a entrainment rate value, a surface roughness value, a material parameter value and a hardness value;
the neural network calculation module is used for inputting the obtained current input load value, the entrainment rate value, the surface roughness value, the material parameter value and the hardness value into the trained neural network model to obtain a film thickness value;
and the output module is used for outputting the film thickness value.
Optionally, the numerical simulation computation module is further configured to:
s1, obtaining a first film thickness value by using the obtained initial input load value and a film thickness equation;
s2, obtaining a lubricating grease fluid pressure value by using the first film thickness value and a Reynolds equation, and obtaining a microprotrusion contact pressure value by using the first film thickness value and a microprotrusion contact stress model equation;
s3, obtaining an input load value by using the lubricating grease fluid pressure value, the microprotrusion contact pressure value and a load balance equation;
and S4, performing iteration processing according to S1, S2 and S3 until the difference value of the fluid pressure values of the lubricating grease before and after the iteration, the difference value of the contact pressure values of the microprotrusions before and after the iteration and the difference value of the input load values before and after the iteration are all smaller than the preset difference value, and taking the film thickness value obtained by the iteration processing as the film thickness value corresponding to the initial input load value.
Optionally, the neural network training module is further configured to:
inputting the multiple groups of input values and the corresponding film thickness values into a neural network model;
optimizing the weight value and the threshold value of the neural network model by using a genetic algorithm;
and transmitting the corresponding weight and threshold value when the difference value between the predicted film thickness value output from the neural network model and the input film thickness value meets the training precision requirement to the neural network model to obtain the trained neural network model.
According to a third aspect of the present invention, there is provided a grease lubricant film thickness determination apparatus comprising: a memory and a processor, wherein the memory stores executable instructions that control the processor to operate to perform the method of determining grease lubricant film thickness according to any one of the first aspect.
The method and the device have the advantages that the film thickness in the lubricating process can be quickly and accurately determined, and the lubricating mechanism can be accurately judged in time, so that the lubricating parameters or working condition parameters are adjusted, and the workpiece can run in a good lubricating range.
Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a process flow diagram of a method of determining a grease lubricant film thickness according to an embodiment of the present invention.
Fig. 2 is a comparison graph of the film thickness value predicted by the trained neural network model and the actual film thickness value.
Fig. 3 is a schematic structural diagram of a grease lubricant film thickness determination apparatus according to an embodiment of the present invention.
Fig. 4 is a schematic diagram showing a hardware configuration of the apparatus for determining the thickness of the grease lubricant film according to an embodiment of the present invention.
Detailed Description
Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
< method >
Fig. 1 is a process flow diagram of a method of determining a grease lubricant film thickness according to an embodiment of the present invention.
According to fig. 1, the method for determining the thickness of the grease lubricant film at least comprises the following steps:
and step S1100, determining film thickness values under multiple groups of different input parameters according to a numerical simulation algorithm.
The step S1100 may specifically include the following steps:
and S1, obtaining a first film thickness value by using the obtained initial input load value and the film thickness equation.
In the embodiment of the invention, the initial minimum contact gap value of the contact surface of the friction pair is obtained, and then the initial minimum contact gap value and the initial input load value are input into the film thickness equation to obtain the film thickness value.
The film thickness equation is specifically:
wherein h is0Is the initial minimum contact gap value of the contact surface of the friction pair, R is the equivalent radius, R1、R2Respectively, the curvature radius of the contact position of the friction pair, v (x, y) is an elastic deformation equation of the contact surface of the friction pair, E' is an equivalent elastic modulus, E1、E2Respectively, modulus of elasticity, v, of friction pairs1、v2Poisson's ratio, p, of friction pairs, respectivelyt(s, t) is an input load value, h (x, y) is a film thickness value corresponding to a certain point to be measured in the film thickness calculation region, s represents a length value of the calculation region in the x-axis direction of the film thickness calculation region, and t represents a length value of the calculation region in the y-axis direction of the film thickness calculation region.
S2, obtaining a grease fluid pressure value by using the first film thickness value and a Reynolds equation, and obtaining a microprotrusion contact pressure value by using the first film thickness value and a microprotrusion contact stress model equation.
In the embodiment of the invention, the rheological index value of the lubricating grease, the initial density value of the lubricating grease, the initial viscosity value of the lubricating grease, the surface roughness value of the contact surface of the friction pair and the entrainment rate value are obtained, and then the first film thickness value, the rheological index value of the lubricating grease, the initial density value of the lubricating grease, the initial viscosity value of the lubricating grease, the surface roughness value of the contact surface of the friction pair and the entrainment rate value are input into a Reynolds equation to obtain the fluid pressure value of the lubricating grease.
The Reynolds equation is specifically:
wherein n is the rheological index of the grease, phixA value of a fluid pressure index in a direction parallel to the flow direction of the grease, phiyValue of fluid pressure index, σ, in a direction perpendicular to the flow direction of the grease1、σ2Is the surface roughness value of the friction pair, p0Is the initial density value of the grease,. eta0The value of the initial viscosity of the grease is shown, h is the value of the film thickness, and p is the value of the fluid pressure of the grease.
In the embodiment of the invention, after the pressure value p of the lubricating grease fluid is obtained by using the Reynolds equation, the pressure value p of the lubricating grease fluid is input into the lubricating grease density equation, and the density of the lubricating grease is obtained. And when the next iteration processing is carried out, replacing the density of the grease used in the last iteration processing with the density of the grease obtained by calculation.
The grease compaction process is as follows:
where ρ is0The initial density value of the grease is A, B is a constant, wherein A is 0.6 multiplied by 10-9Pa-1,B＝1.7×10-9Pa-1，PHAnd p is the value of the grease fluid pressure for the maximum Hertz contact pressure.
In the embodiment of the invention, after the pressure value p of the lubricating grease fluid is obtained by using the Reynolds equation, the pressure value p of the lubricating grease fluid is input into the lubricating grease viscosity equation, and the viscosity of the lubricating grease is obtained. And when the next iteration processing is carried out, replacing the viscosity of the lubricating grease used in the previous iteration processing with the calculated viscosity of the lubricating grease.
The grease viscosity equation is as follows:
wherein, taulimIs the ultimate shear stress of the grease,
is the shear strain rate, eta, of the grease0Is the initial viscosity value, z, of the grease0Is a constant, usually 0.68, and p is the grease fluid pressure value.
In the embodiment of the invention, the surface parameter value, the elastic modulus value of the friction pair, the curvature radius value of the microprotrusion, the height value of the microprotrusion, the average gap value of the contact surface of the friction pair, the difference value between the average height of the microprotrusion and the average height of the surface and the hardness value are obtained. And then inputting the first film thickness value, the surface parameter value, the elastic modulus value of the friction pair, the curvature radius value of the microprotrusions, the height value of the microprotrusions, the average gap value of the contact surface of the friction pair, the difference value of the average height of the microprotrusions and the average height of the surface and the hardness value into a microprotrusion contact stress model equation to obtain a microprotrusion contact pressure value.
The microprotrusion contact stress model equation is specified below,
Kh0.454+0.41 ν -formula (5a),
wherein p iscBeta is the surface parameter of the friction pair, usually 0.05, for the value of the microprotrusion contact pressure, v is the Poisson's ratio, omega, of the softer material in the friction paircE' is the equivalent elastic modulus, HdBrinell hardness number, RasIs the radius of curvature of the microprotrusion, σ1、σ2Watch as friction pairThe surface roughness value, h is the film thickness value,
is the difference between the average height of the asperities and the average height of the surface, zs *Is the height of the microprotrusion, phis *(zs *) For height distribution function of the microprotrusions, subject to Gaussian probability density distribution functions, i.e.
Note that the values of α in the formula (5g) correspond to 1.5, 1.425, 1.263, and 1 in the formula (5), respectively.
And S3, obtaining an input load value by using the lubricating grease fluid pressure value, the microprotrusion contact pressure value and a load balance equation.
The load balance equation is as follows:
∫∫pdxdy+∫∫pcdxdy＝∫∫ptdxdy-equation (6),
wherein p is the pressure value of the lubricating grease fluid, pcIs a microprotrusion contact pressure value, ptIs the input load value.
And S4, performing iteration processing according to S1, S2 and S3 until the difference value of the fluid pressure values of the lubricating grease before and after the iteration, the difference value of the contact pressure values of the microprotrusions before and after the iteration and the difference value of the input load values before and after the iteration are all smaller than the preset difference value, and taking the film thickness value obtained by the iteration processing as the film thickness value corresponding to the initial input load value.
In the embodiment of the invention, after the input load value is obtained by calculation by using the load equation corresponding to the formula (6), the input load value is input into the film thickness equation corresponding to the value formula (1) again to obtain the film thickness value. And (4) inputting the film thickness value obtained by the calculation again into a Reynolds equation corresponding to the formula (2) to obtain the pressure value of the lubricating grease fluid. And (4) inputting the film thickness value obtained by the calculation again into a microprotrusion contact stress model equation corresponding to the formula (5) to obtain a microprotrusion contact pressure value. And (4) inputting the calculated lubricating grease fluid pressure value and the microprotrusion contact pressure value into a load equation corresponding to the formula (6), and calculating to obtain an input load value. Then, the difference between the grease pressure value obtained by the calculation and the grease pressure value obtained by the previous calculation, the difference between the microprotrusion contact pressure value obtained by the calculation and the microprotrusion contact pressure value obtained by the previous calculation, and the difference between the input load value obtained by the calculation and the input load value obtained by the previous calculation are respectively calculated. And if the three difference values are all smaller than the preset difference value, stopping the iteration processing, and taking the film thickness value obtained by the iteration processing as the film thickness value corresponding to the initial input load value.
And S1200, training and testing the neural network model by utilizing a plurality of groups of input values and corresponding film thickness values to obtain the trained neural network model, wherein the input values at least comprise an input load value, a entrainment rate value, a surface roughness value, a material parameter value and a hardness value.
In the embodiment of the invention, a plurality of groups of input values and corresponding film thickness values are input into the neural network model. And optimizing the weight and the threshold of the neural network model by using a genetic algorithm. And transmitting the corresponding weight and threshold value when the difference value between the predicted film thickness value output in the neural network model and the input film thickness value meets the training precision requirement to the neural network model to obtain the trained neural network model.
The input to the neural network model is a dimensionalized input value, that is, each input value is dimensionalized by the surface roughness σ of the friction pair.
In the embodiment of the invention, before each input value is input into the neural network model, the input value is normalized according to the following formula,
wherein x ismaxIs the maximum value, x, of the input valuesminIs the minimum value, x, of the input valuesiIs the ith data in the input value, and X is the value after the normalization of the ith data. To be provided withInput load value, xmaxIs the maximum value, x, of the input load valuesminIs the minimum value, x, of the input load valuesiIs the ith input load value.
In the embodiment of the invention, the neural network model is a BP (Back propagation) neural network model. The BP neural network is a multilayer feedforward neural network and is mainly characterized by signal forward transmission and error backward propagation. In forward transmission, an input signal is processed layer by layer from an input layer through a hidden layer until the input signal reaches an output layer, the neuron state of each layer can only affect the neuron state of the next layer, if the output layer cannot obtain expected output, backward propagation is carried out, and a network weight and a threshold are adjusted according to a prediction error, so that the predicted output of the BP neural network continuously approaches the expected output.
The genetic algorithm introduces the biological evolution principle of the elimination of the superiority and the inferiority in the nature and the survival of the fittest into a coding series group formed by optimized parameters, and screens individuals through selection, intersection and variation in the inheritance according to a fitness function selected, so that the individuals with good fitness values are reserved, the individuals with poor fitness values are eliminated, the new group integrates the information of the previous generation and is superior to the previous generation, and the process is repeated until the conditions are met.
The optimization of the BP neural network by the genetic algorithm is divided into three parts, namely determination of the BP neural network structure, optimization of the genetic algorithm and prediction of the BP neural network.
The BP neural network structure determining part determines the BP neural network structure according to the number of input and output parameters of the fitting function, and further determines the length of the genetic algorithm individual. The genetic algorithm optimization refers to the optimization of the weight and the threshold of the BP neural network by using the genetic algorithm, each individual in the population comprises all the weight and the threshold of one network, and the individual calculates the individual fitness value through a fitness function. The genetic algorithm finds out the individuals corresponding to the optimal fitness value through selection, intersection and mutation operations. And BP neural network prediction is to obtain the optimal individual to neural network initial weight and threshold assignment by using a genetic algorithm, and predict function output after network training.
Fig. 2 is a comparison graph of the film thickness value predicted by the trained neural network model and the actual film thickness value.
As shown in fig. 2, the abscissa represents the film thickness value predicted by the trained neural network model, and the ordinate represents the film thickness value calculated by the numerical simulation algorithm. As can be seen from fig. 2, the film thickness value predicted by using the trained neural network model is substantially the same as the film thickness value calculated by using the numerical simulation algorithm.
And step S1300, inputting the obtained current input load value, the entrainment rate value, the surface roughness value, the material parameter value and the hardness value into the trained neural network model to obtain the film thickness value.
Step S1400, outputting the film thickness value.
According to the method for determining the thickness of the lubricating grease film, provided by the embodiment of the invention, the thickness of the film in the lubricating process can be rapidly and accurately determined, and the lubricating mechanism can be accurately judged in time, so that the lubricating parameters or working condition parameters are adjusted, and the workpiece can run in a good lubricating range.
< apparatus >
Fig. 3 is a schematic structural diagram of a grease lubricant film thickness determination apparatus according to an embodiment of the present invention. According to fig. 3, the device comprises at least: a numerical simulation calculation module 310, a neural network training module 320, a neural network calculation module 330, and an output module 340.
The numerical simulation calculation module 310 is used for determining film thickness values under a plurality of groups of different input parameters according to a numerical simulation algorithm.
The neural network training module 320 is configured to train the neural network model by using multiple sets of input values and corresponding film thicknesses to obtain the trained neural network model, where the input values at least include an input load value, a entrainment rate value, a surface roughness value, a material parameter value, and a hardness value.
The neural network calculation module 330 is configured to input the obtained current input load value, the obtained entrainment rate value, the obtained surface roughness value, the obtained material parameter value, and the obtained hardness value into the trained neural network model to obtain the film thickness value.
The output module 340 is used for outputting the film thickness value.
In an embodiment of the present invention, the numerical simulation calculating module 310 is further configured to obtain, at S1, a first film thickness value by using the obtained initial input load value and the film thickness equation;
s2, obtaining a lubricating grease fluid pressure value by using the first film thickness value and a Reynolds equation, and obtaining a microprotrusion contact pressure value by using the first film thickness value and a microprotrusion contact stress model equation;
s3, obtaining an input load value by using a lubricating grease fluid pressure value, a microprotrusion contact pressure value and a load balance equation;
and S4, performing iteration processing according to S1, S2 and S3 until the difference value of the fluid pressure values of the lubricating grease before and after the iteration, the difference value of the contact pressure values of the microprotrusions before and after the iteration and the difference value of the input load values before and after the iteration are all smaller than the preset difference value, and taking the film thickness value obtained by the iteration processing as the film thickness value corresponding to the initial input load value.
In an embodiment of the present invention, the neural network training module 320 is further configured to input a plurality of sets of input values and corresponding film thickness values into the neural network model; optimizing the weight and the threshold of the neural network model by using a genetic algorithm; and transmitting the corresponding weight and threshold value when the difference value between the predicted film thickness value output in the neural network model and the input film thickness value meets the training precision requirement to the neural network model to obtain the trained neural network model.
Fig. 4 is a schematic diagram showing a hardware configuration of the apparatus for determining the thickness of the grease lubricant film according to an embodiment of the present invention. Referring to fig. 4, the apparatus includes at least: a memory 420 and a processor 410, wherein the memory 420 stores executable instructions that control the processor 410 to operate to perform any of the above-described methods of determining grease lubrication film thickness.
The present invention may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied therewith for causing a processor to implement various aspects of the present invention.
The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
The computer program instructions for carrying out operations of the present invention may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing an electronic circuit, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), with state information of computer-readable program instructions, which can execute the computer-readable program instructions.
Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, by software, and by a combination of software and hardware are equivalent.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.
Claims (8)
1. A method for determining a grease lubricant film thickness, comprising:
determining film thickness values under a plurality of groups of different input parameters according to a numerical simulation algorithm;
training the neural network model by utilizing a plurality of groups of input values and corresponding film thickness values to obtain the trained neural network model, wherein the input values at least comprise an input load value, a entrainment speed value, a surface roughness value, a material parameter value and a hardness value;
inputting the obtained current input load value, the entrainment speed value, the surface roughness value, the material parameter value and the hardness value into the trained neural network model to obtain a film thickness value;
outputting the film thickness value;
wherein, according to the numerical simulation algorithm, the film thickness values under a plurality of groups of different input parameters are determined, including:
s1, obtaining a first film thickness value by using the obtained initial input load value and a film thickness equation;
s2, obtaining a lubricating grease fluid pressure value by using the first film thickness value and a Reynolds equation, and obtaining a microprotrusion contact pressure value by using the first film thickness value and a microprotrusion contact stress model equation;
s3, obtaining an input load value by using the lubricating grease fluid pressure value, the microprotrusion contact pressure value and a load balance equation;
and S4, performing iteration processing according to S1, S2 and S3 until the difference value of the fluid pressure values of the lubricating grease before and after the iteration, the difference value of the contact pressure values of the microprotrusions before and after the iteration and the difference value of the input load values before and after the iteration are all smaller than the preset difference value, and taking the film thickness value obtained by the iteration processing as the film thickness value corresponding to the initial input load value.
2. The method of claim 1, wherein obtaining the film thickness value using the obtained initial input load value and the film thickness equation comprises:
acquiring an initial minimum contact clearance value of the contact surface of the friction pair;
and inputting the initial minimum contact gap value and the initial input load value into the film thickness equation to obtain a film thickness value.
3. The method of claim 1, wherein using the first film thickness value and a reynolds equation to obtain a grease fluid pressure value comprises:
obtaining a rheological index value of the grease, an initial density value of the grease, an initial viscosity value of the grease, a surface roughness value of a contact surface of a friction pair and a value of a entrainment rate;
and inputting the first film thickness value, the rheological index value of the lubricating grease, the initial density value of the lubricating grease, the initial viscosity value of the lubricating grease, the surface roughness value of the contact surface of the friction pair and the entrainment rate value into the Reynolds equation to obtain the fluid pressure value of the lubricating grease.
4. The method of claim 1, wherein obtaining a dimple contact pressure value using the first film thickness value and a dimple contact stress model equation comprises:
obtaining a surface parameter value of the friction pair, an elastic modulus value of the friction pair, a curvature radius value of the microprotrusions, a height value of the microprotrusions, an average gap value of a contact surface of the friction pair, a difference value of the average height of the microprotrusions and the average height of the surface and a hardness value of the friction pair;
and inputting the first film thickness value, the surface parameter value, the elastic modulus value of the friction pair, the curvature radius value of the microprotrusion, the height value of the microprotrusion, the average gap value of the contact surface of the friction pair, the difference value between the average height of the microprotrusion and the average height of the surface and the hardness value into a microprotrusion contact stress model equation to obtain a microprotrusion contact pressure value.
5. The method according to any one of claims 1-4, wherein training the neural network model using the plurality of sets of input values and corresponding film thickness values to obtain the trained neural network model comprises:
inputting the multiple groups of input values and the corresponding film thickness values into a neural network model;
optimizing the weight and the threshold of the neural network model by using a genetic algorithm;
and transmitting the corresponding weight and threshold value when the difference value between the predicted film thickness value output from the neural network model and the input film thickness value meets the training precision requirement to the neural network model to obtain the trained neural network model.
6. A device for determining a grease lubrication film thickness, comprising:
the numerical simulation calculation module is used for determining film thickness values under a plurality of groups of different input parameters according to a numerical simulation algorithm;
the neural network training module is used for training the neural network model by utilizing a plurality of groups of input values and corresponding film thickness values to obtain the trained neural network model, wherein the input values at least comprise an input load value, a entrainment rate value, a surface roughness value, a material parameter value and a hardness value;
the neural network calculation module is used for inputting the obtained current input load value, the entrainment rate value, the surface roughness value, the material parameter value and the hardness value into the trained neural network model to obtain a film thickness value;
the output module is used for outputting the film thickness value;
wherein the numerical simulation computation module is further configured to:
s1, obtaining a first film thickness value by using the obtained initial input load value and a film thickness equation;
s2, obtaining a lubricating grease fluid pressure value by using the first film thickness value and a Reynolds equation, and obtaining a microprotrusion contact pressure value by using the first film thickness value and a microprotrusion contact stress model equation;
s3, obtaining an input load value by using the lubricating grease fluid pressure value, the microprotrusion contact pressure value and a load balance equation;
and S4, performing iteration processing according to S1, S2 and S3 until the difference value of the fluid pressure values of the lubricating grease before and after the iteration, the difference value of the contact pressure values of the microprotrusions before and after the iteration and the difference value of the input load values before and after the iteration are all smaller than the preset difference value, and taking the film thickness value obtained by the iteration processing as the film thickness value corresponding to the initial input load value.
7. The apparatus of claim 6, wherein the neural network training module is further configured to:
inputting the multiple groups of input values and the corresponding film thickness values into a neural network model;
optimizing the weight and the threshold of the neural network model by using a genetic algorithm;
and transmitting the corresponding weight and threshold value when the difference value between the predicted film thickness value output from the neural network model and the input film thickness value meets the training precision requirement to the neural network model to obtain the trained neural network model.
8. A device for determining a grease lubrication film thickness, comprising: a memory and a processor, wherein the memory stores executable instructions that control the processor to operate to perform the method of determining grease lubrication film thickness according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811354644.5A CN109598031B (en) | 2018-11-14 | 2018-11-14 | Method and device for determining thickness of grease lubricating film |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811354644.5A CN109598031B (en) | 2018-11-14 | 2018-11-14 | Method and device for determining thickness of grease lubricating film |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109598031A CN109598031A (en) | 2019-04-09 |
| CN109598031B true CN109598031B (en) | 2021-01-29 |
Family
ID=65958588
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811354644.5A Active CN109598031B (en) | 2018-11-14 | 2018-11-14 | Method and device for determining thickness of grease lubricating film |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109598031B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116738611B (en) * | 2023-06-09 | 2024-02-02 | 江苏海洋大学 | Design method of high-load low-friction pair with self-repairing ultra-smooth surface |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101776508A (en) * | 2010-01-19 | 2010-07-14 | 西安交通大学 | Optical-mechanical-electrical multi-parameter accurate monitoring device of rotating machine |
| JP6111717B2 (en) * | 2013-02-13 | 2017-04-12 | 新日鐵住金株式会社 | Arithmetic processing method, arithmetic processing device, and program |
| CN104568444B (en) * | 2015-01-28 | 2017-02-22 | 北京邮电大学 | Method for extracting fault characteristic frequencies of train rolling bearings with variable rotational speeds |
| CN105447572A (en) * | 2015-12-21 | 2016-03-30 | 广东智造能源科技研究有限公司 | Wind power prediction system and method based on neural network optimized by genetic algorithm |
| US10230045B2 (en) * | 2017-04-21 | 2019-03-12 | Gyrfalcon Technology Inc. | Process of fabricating embedded spin transfer torque memory for cellular neural network based processing unit |
| CN107687368B (en) * | 2017-10-16 | 2020-09-11 | 北京理工大学 | Method for predicting friction loss of radial sealing sheet of microminiature rotor engine |
-
2018
- 2018-11-14 CN CN201811354644.5A patent/CN109598031B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109598031A (en) | 2019-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kharoufeh et al. | Stochastic models for degradation-based reliability | |
| US11423330B2 (en) | Performance score determiner for binary signal classifiers | |
| WO2015088841A1 (en) | Personalized machine learning models | |
| WO2015126858A1 (en) | Personalized machine learning system | |
| Sta˚ hl et al. | A lubricant model considering wall-slip in EHL line contacts | |
| US20170278067A1 (en) | Monitoring activity to detect potential user actions | |
| WO2020257782A1 (en) | Factory risk estimation using historical inspection data | |
| US11455561B2 (en) | Alerting to model degradation based on distribution analysis using risk tolerance ratings | |
| Londhe et al. | Extended hertz theory of contact mechanics for case-hardened steels with implications for bearing fatigue life | |
| US20140025418A1 (en) | Clustering Based Resource Planning, Work Assignment, and Cross-Skill Training Planning in Services Management | |
| US20210048811A1 (en) | Model generation device for life prediction, model generation method for life prediction, and recording medium storing model generation program for life prediction | |
| De La Guerra Ochoa et al. | Optimising lubricated friction coefficient by surface texturing | |
| US20220129316A1 (en) | Workload Equivalence Class Identification For Resource Usage Prediction | |
| CN109598031B (en) | Method and device for determining thickness of grease lubricating film | |
| US20210357699A1 (en) | Data quality assessment for data analytics | |
| JP7276483B2 (en) | LEARNING DEVICE, CLASSIFIER, LEARNING METHOD AND LEARNING PROGRAM | |
| Houpert | Hydrodynamic load calculation in rolling element bearings | |
| Choo et al. | The influence of longitudinal roughness in thin-film, mixed elastohydrodynamic lubrication | |
| Lee et al. | Remaining useful life estimation for ball bearings using feature engineering and extreme learning machine | |
| Abdel-Hameed | Degradation processes: An overview | |
| US11768917B2 (en) | Systems and methods for alerting to model degradation based on distribution analysis | |
| US20220058519A1 (en) | Open feature library management | |
| Miclea et al. | A new approach for assessing function-cost correlation in product value analysis | |
| US20200134480A1 (en) | Apparatus and method for detecting impact factor for an operating environment | |
| US11256597B2 (en) | Ensemble approach to alerting to model degradation |
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 | ||
| GR01 | Patent grant |