CN108416178A - A kind of mechanical elastic vehicle wheel Design of Structural parameters method - Google Patents
A kind of mechanical elastic vehicle wheel Design of Structural parameters method Download PDFInfo
- Publication number
- CN108416178A CN108416178A CN201810407188.XA CN201810407188A CN108416178A CN 108416178 A CN108416178 A CN 108416178A CN 201810407188 A CN201810407188 A CN 201810407188A CN 108416178 A CN108416178 A CN 108416178A
- Authority
- CN
- China
- Prior art keywords
- wheel
- structural parameters
- mechanical
- finite element
- vehicle wheel
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft 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
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Aviation & Aerospace Engineering (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Automation & Control Theory (AREA)
- Tires In General (AREA)
Abstract
The invention discloses a kind of mechanical elastic vehicle wheel Design of Structural parameters methods, include the following steps：S1, mechanical elastic vehicle wheel finite element model is established；S2, the gathering simulation operating mode for establishing training sample；S3, suitable training sample is selected using Uniform ity Design Method；S4, adaptive neural network algorithm is established；S5, network model training and interpretation of result.The method of the present invention is simple, it is easy to implement, have a good application prospect.
Description
Technical field
The invention belongs to wheel optimized design technical fields, and in particular to a kind of mechanical elastic vehicle wheel structure parameter optimizing is set
Meter method.
Background technology
The design feature and its bearing mode of mechanical elastic vehicle wheel are determined when using different Wheel-band wheel construction parameters, elasticity
When changing structural parameters and the combination of hinge set structural parameters, mechanical characteristic will also change correspondingly.Wheel-band takes turns section width, height, bullet
Property ring section width, height, hinge set length, width and number have a major impact wheel mechanical characteristic, currently, mechanical elasticity
Structural parameters during wheel design are based only on the experiment adjustment that simple theoretical calculation adds model machine, and there are precision
It is low, the shortcomings of poor performance.It is beneficial to preferably meet vehicle to wheel to the Design of Structural parameters of mechanical elastic vehicle wheel
The matching of performance requires and the optimization of subsequent car wheel structure.
Neural network is the mainstream of nonlinear science and computational intelligence scientific research, is good at the data by large amount of complex
Classified and finds that its rule, any nonlinear function of programmable single-chip system have self-organizing, adaptive, associative memory, Error Tolerance
And the advantages that parallel processing capability.By establish in input layer comprising Wheel-band take turns section height setion width, elastic ring section height setion width,
The mechanical elastic vehicle wheel neural network model of hinge length, width and number is realized to the mechanical elastic with Different structural parameters
The analysis of property wheel mechanical characteristic.
Invention content
Goal of the invention：In order to overcome the deficiencies in the prior art, wheel design efficiency of research and development, precision are improved, is avoided
The blindness of research and development, instructs the wheel of tire supplier to match vehicle performance design work, and the present invention provides a kind of machinery
Elastic wheel Design of Structural parameters method.
Technical solution：To achieve the above object, the technical solution adopted by the present invention is：
A kind of mechanical elastic vehicle wheel Design of Structural parameters method, includes the following steps：
S1, mechanical elastic vehicle wheel finite element model is established；Mechanical elastic vehicle wheel structure simply include Wheel-band wheel, hinge set and
Outstanding hub；
S2, the gathering simulation operating mode for establishing training sample；Simulation architecture parameter includes Wheel-band wheel constructions parameter, elastic ring section
Parameter and hinge set parameter；
S3, training sample is obtained using Uniform ity Design Method；
S4, adaptive neural network algorithm is established；
S5, network model training are analyzed with result verification.
Further, step S2 is specifically included：
S21, the finite element simulation for carrying out different Wheel-band wheels section widths；
S22, the finite element simulation for carrying out different Wheel-band wheels profile heights；
S23, the finite element simulation for carrying out different rubber material attributes, include the coefficient of rigidity of tire tread material；
S24, the finite element simulation for carrying out different elastic ring widths；
S25, the finite element simulation for carrying out different elastic ring height；
S26, the finite element simulation for carrying out different hinge set length；
S27, the finite element simulation for carrying out different hinge set width；
S28, the finite element simulation for carrying out different hinge set numbers；
S29, the wheel mechanics characteristic index parameter under several groups Different structural parameters composite condition is obtained.
Further, step S4 is specifically included：
S41, error backward propagation method model is established；
S42, momentum arithmetic method is established, makes network when being modified to weights, can consider error in gradient
Effect, and can consider the influence of its variation tendency on error surface；
S43, adaptation mechanism is established, e-learning rate is made adaptively to be adjusted according to error change.
Further, the error backward propagation method model is：
The reality output of output neuron is：
The error function of output layer is：
Wherein, xi(i=1,2 ..., m) be input layer, yj(j=1,2 ..., p) be hidden layer node export, hk
(k=1,2 ..., n) be node desired output, Rk(k=1,2 ..., n) it is reality output；
It to make error constantly reduce, is adjusted, corrects as follows along the negative gradient direction of weights：
Wherein, η is learning rate, δk=(hk-Rk)f′(netk),Network after being adjusted connects
Connecing weights is：
Wherein, T is frequency of training.
Further, the weighed value adjusting formula of momentum arithmetic is：
Wherein：For factor of momentum；N is frequency of training；▽f(wij(n-1)) it is the gradient of error function.
Further, the learning rate adaptation mechanism used in the training process for：
E (N) is the error of the n-th step in formula.
Further, step S3 is specifically included：
S31, each factor level for influencing wheel mechanical characteristic is determined；
S32, each factor level is numbered；
S33, according to influence factor number and factor level number, select matching orthogonal arrage；
S33, the sample space for being used for neural metwork training is determined.
Further, step S5 is specifically included：
S51, network training is carried out；
S52, network model verification；
S53, interpretation of result, wheel when specifically utilizing the generalization ability of network model to Different structural parameters are carried out
Mechanical characteristic analyzed, including：
The wheel mechanical characteristic of different Wheel-band wheels section height setion widths,
The wheel mechanical characteristic of different elastic ring section height setion widths,
The wheel mechanical characteristic of different rubber layer material properties, includes the coefficient of rigidity of tire tread material,
The wheel mechanical characteristic of different hinge set length,
Wheel mechanical characteristic when different hinge set width,
The wheel mechanical characteristic of different hinge set numbers；
S54, car wheel structure parameter improvement.
Advantageous effect：A kind of mechanical elastic vehicle wheel Design of Structural parameters method provided by the invention, with the prior art
It compares, has the advantage that：
1, design method is simple, is easy to implement and promotes；
2, build car wheel structure parameter and mechanics of tire characteristic mapping relations, instruct wheel production, design and
With work.
Description of the drawings
Fig. 1 is the car wheel structure method for optimally designing parameters flow chart of the present invention；
Fig. 2 is wheel finite element dynamics specificity analysis flow chart；
Fig. 3 is wheel finite element structure schematic diagram；
In figure, 1- Wheel-band wheels, 2- hinge sets, 3- hangs hub；
Fig. 4 is Wheel-band wheel section structure diagrams；
In figure, 1- Wheel-band wheels, 4- rubber layers, 5- elastic rings；
Fig. 5 is hinge set structural schematic diagram；
Fig. 6 is adaptive neural network algorithm schematic diagram.
Specific implementation mode
The design method of the present invention includes the following steps：S1, mechanical elastic vehicle wheel finite element model is established；S2, instruction is established
Practice the gathering simulation operating mode of sample；S3, suitable training sample is selected using Uniform ity Design Method；S4, adaptive neural network is established
Network algorithm；S5, network model training and interpretation of result.The method of the present invention is simple, it is easy to implement, there is good application before
Scape.The present invention is further described with reference to the accompanying drawings and examples.
Embodiment
As shown in Figure 1, a kind of mechanical elastic vehicle wheel Design of Structural parameters method of the present invention, includes the following steps：
S1, mechanical elastic vehicle wheel finite element model is established；Specifically include following sub-step：
S11, finite element model mechanical characteristic analysis flow chart are as shown in Fig. 2, in the reliability premise for ensureing analysis result
Under to its mechanical elastic vehicle wheel structure carry out suitably simplify；
S12, as one embodiment, as shown in figure 3, the mechanical elastic vehicle wheel finite element model primary structure established includes
Wheel-band wheels, hinge set, outstanding hub；
S13, verification experimental verification is carried out to the mechanical elasticity safety wheel simulation model of foundation.
S2, the gathering simulation operating mode for establishing training sample；Specifically include following sub-step：
As one embodiment, as shown in figure 4, the Wheel-band wheel constructions parameter includes mainly Wheel-band wheel section widths B, height H,
Rubber layer material properties, elastic ring dispersion of distribution b, height h.
S21, the finite element simulation for carrying out different Wheel-band wheels section widths；.
S22, the finite element simulation for carrying out different Wheel-band wheels profile heights；
S23, different rubber material attributes are carried out, such as：The finite element simulation of the coefficient of rigidity of tire tread material；
S24, the finite element simulation for carrying out different elastic ring widths；
S25, the finite element simulation for carrying out different elastic ring height；
As one embodiment, as shown in figure 5, the hinge set structural parameters include mainly hinge set length L, width,
Hinge set number.
S26, the finite element simulation for carrying out different hinge set length；
S27, the finite element simulation for carrying out different hinge set width；
S28, the finite element simulation for carrying out different hinge set numbers；
The design parameter of finite element stimulation is carried out in given section value, it is as shown in table 1 with specific reference to interval.
1 car wheel structure parameter value range of table
| Parameter | Value range |
| Wheel-band takes turns section width | 310~320mm |
| Wheel-band takes turns profile height | 70~90mm |
| Original shear modulus | 1.04~1.82Mpa |
| Elastic ring width | 20~30mm |
| Elastic ring height | 15~20mm |
| Hinge set length | 120~150mm |
| Hinge set width | 45~55mm |
| Hinge set number | 12~18 |
S29, the wheel mechanics characteristic index parameter under several groups different wheel structural parameters composite condition is obtained.
S3, suitable training sample is selected using Uniform ity Design Method.Specifically include following sub-step：
S31, each factor level for influencing wheel mechanical characteristic is determined；Wherein, relevant factor includes：It is high wide that Wheel-band takes turns section
Than H/B, elastic ring section height setion width is h/b, original shear modulus, hinge set length, width, number etc., factor level difference
4 levels are set；
It is assumed that the basic structures size such as the Wheel-band wheels radius of wheel finite element model, Wheel-band wheel section widths B is definite value, by changing
Become Wheel-band and take turns profile height H, obtains different Wheel-band wheel section height setion widths H/B；In the case where elastic ring cross-sectional area is constant, pass through
Change elastic ring profile height h and width b, it is h/b to obtain different elastic ring section height setion widths；It is uniaxially stretched examination based on rubber
Data are tested, tool is recognized using the material model of finite element analysis software, it is normal that Mooney-Rivlin material models is calculated
Number, the influence for research rubber layer original shear modulus to wheel cornering behavior, makees adjustment appropriate to material model constant, asks
Go out different original shear modulus G；Structure size by changing hinge set obtains different hinge set length, width, number
Hinge set；Mechanical elastic vehicle wheel initial model is made into corresponding structure size modification, obtains corresponding design scheme model, specifically
Design scheme is as shown in table 2.
The factor level of 1 car wheel structure parameter of table
S32, each factor level is numbered；
S33, according to influence factor number and factor level number, select matching orthogonal arrage
S34, the sample space for being used for neural metwork training is determined.
S4, adaptive neural network algorithm is established；Specifically include following sub-step：
S41, as one embodiment, as shown in fig. 6, establishing error backward propagation method model：
The reality output of output neuron is：
The error function of output layer is：
Wherein, xi(i=1,2 ..., m) be input layer, m be input layer number, yj(j=1,2 ..., p) be
Hidden layer node exports, and p is hidden layer node number, hk(k=1,2 ..., n) be node desired output, Rk(k=1,
2 ..., n) be reality output, n be output layer node number；wjiBetween i-th of node of j-th of node of input layer and hidden layer
Connection weight, θjFor the threshold value of j-th of node of hidden layer, netjFor hidden layer input variable, ukjFor k-th of node of hidden layer with
Connection weight between j-th of node of output layer, θkFor the threshold value of k-th of node of output layer, netkFor output layer input variable.
It to make error constantly reduce, is adjusted, corrects as follows along the negative gradient direction of weights：
Wherein, η is learning rate, δk=(hk-Rk)f′(netk),Network after being adjusted connects
Connecing weights is：
Wherein, T is frequency of training.
S42, momentum arithmetic method is established, makes network when being modified to weights, can consider error in gradient
Effect, and can consider the influence of its variation tendency on error surface.The weighed value adjusting formula of momentum arithmetic is：
Wherein：For factor of momentum；T is frequency of training；▽f(wij(T-1)) it is the gradient of error function.Using additional dynamic
After amount method, the adjustings of weights will change towards the mean direction of error surface bottom, can be with when network weight enters flat region
The appearance for preventing Δ w=0 helps that network is made to jump out from error surface local minimum.
S43, adaptation mechanism is established, e-learning rate is made adaptively to be adjusted according to error change.In training process
The middle learning rate adaptation mechanism used for：
E (N) is the error of the n-th step in formula.
S5, network model training and interpretation of result.Specifically include following sub-step：
S51, network training is carried out；
S52, network model verification；
S53, using the generalization ability of network model to Different structural parameters when wheel mechanical characteristic analyze,
Including：
The wheel mechanical characteristic of different Wheel-band wheels section height setion widths,
The wheel mechanical characteristic of different elastic ring section height setion widths,
Different rubber layer material properties, such as：The wheel mechanical characteristic of the coefficient of rigidity of tire tread material,
The wheel mechanical characteristic of different hinge set length,
Wheel mechanical characteristic when different hinge set width,
The wheel mechanical characteristic of different hinge set numbers,
It is special to mechanical elastic vehicle wheel lateral deviation in the case where vertical load is 15kN operating modes according to structure simulation scheme shown in table 2
Property carry out simulation calculation, and to emulation data handle, obtain wheel cornering behavior evaluation index (including cornering stiffness,
Lateral force peak value, aligning stiffness and aligning torque peak value).Cornering behavior evaluation index under each structural parameters different level
It is as shown in table 3 with reference to value range.
The evaluation index of cornering behavior under 3 each structural parameters different level of table refers to value range
S54, car wheel structure parameter improvement.
Those skilled in the art of the present technique are it is understood that unless otherwise defined, all terms used herein (including skill
Art term and scientific terminology) there is meaning identical with the general understanding of the those of ordinary skill in fields of the present invention.Also
It should be understood that those terms such as defined in the general dictionary should be understood that with in the context of the prior art
The consistent meaning of meaning, and unless defined as here, will not be explained with the meaning of idealization or too formal.
The above is only a preferred embodiment of the present invention, it should be pointed out that：For the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (8)
1. a kind of mechanical elastic vehicle wheel Design of Structural parameters method, it is characterised in that：Include the following steps：
S1, mechanical elastic vehicle wheel finite element model is established；Mechanical elastic vehicle wheel structure simply includes Wheel-band wheels, hinge set and hangs
Hub；
S2, the gathering simulation operating mode for establishing training sample；Simulation architecture parameter includes Wheel-band wheel constructions parameter, elastic ring section parameter
With hinge set parameter；
S3, training sample is obtained using Uniform ity Design Method；
S4, adaptive neural network algorithm is established；
S5, network model training are analyzed with result verification.
2. a kind of mechanical elastic vehicle wheel Design of Structural parameters method according to claim 1, which is characterized in that step
S2 is specifically included：
S21, the finite element simulation for carrying out different Wheel-band wheels section widths；
S22, the finite element simulation for carrying out different Wheel-band wheels profile heights；
S23, the finite element simulation for carrying out different rubber material attributes, include the coefficient of rigidity of tire tread material；
S24, the finite element simulation for carrying out different elastic ring widths；
S25, the finite element simulation for carrying out different elastic ring height；
S26, the finite element simulation for carrying out different hinge set length；
S27, the finite element simulation for carrying out different hinge set width；
S28, the finite element simulation for carrying out different hinge set numbers；
S29, the wheel mechanics characteristic index parameter under several groups Different structural parameters composite condition is obtained.
3. a kind of mechanical elastic vehicle wheel Design of Structural parameters method according to claim 1, which is characterized in that step
S4 is specifically included：
S41, error backward propagation method model is established；
S42, momentum arithmetic method is established, makes network when being modified to weights, can consider effect of the error in gradient,
The influence of its variation tendency on error surface can be considered again；
S43, adaptation mechanism is established, e-learning rate is made adaptively to be adjusted according to error change.
4. a kind of mechanical elastic vehicle wheel Design of Structural parameters method according to claim 3, which is characterized in that described
Error backward propagation method model is：
The reality output of output neuron is：
The error function of output layer is：
Wherein, xi(i=1,2 ..., m) be input layer, yj(j=1,2 ..., p) be hidden layer node export, hk(k=
1,2 ..., n) be node desired output, Rk(k=1,2 ..., n) it is reality output；
It to make error constantly reduce, is adjusted, corrects as follows along the negative gradient direction of weights：
Wherein, η is learning rate, δk=(hk-Rk)f′(netk),Network connection power after being adjusted
Value is：
Wherein, T is frequency of training.
5. a kind of mechanical elastic vehicle wheel Design of Structural parameters method according to claim 3, which is characterized in that additional
The weighed value adjusting formula of momentum term is：
Wherein：For factor of momentum；N is frequency of training；For the gradient of error function.
6. a kind of mechanical elastic vehicle wheel Design of Structural parameters method according to claim 3, which is characterized in that instructing
Practice the learning rate adaptation mechanism that uses in the process for：
E (N) is the error of the n-th step in formula.
7. a kind of mechanical elastic vehicle wheel Design of Structural parameters method according to claim 1, which is characterized in that step
S3 is specifically included：
S31, each factor level for influencing wheel mechanical characteristic is determined；
S32, each factor level is numbered；
S33, according to influence factor number and factor level number, select matching orthogonal arrage；
S33, the sample space for being used for neural metwork training is determined.
8. a kind of mechanical elastic vehicle wheel Design of Structural parameters method according to claim 1, which is characterized in that step
S5 is specifically included：
S51, network training is carried out；
S52, network model verification；
S53, interpretation of result is carried out, the power of wheel when specifically utilizing the generalization ability of network model to Different structural parameters
Characteristic is learned to be analyzed, including：
The wheel mechanical characteristic of different Wheel-band wheels section height setion widths,
The wheel mechanical characteristic of different elastic ring section height setion widths,
The wheel mechanical characteristic of different rubber layer material properties, includes the coefficient of rigidity of tire tread material,
The wheel mechanical characteristic of different hinge set length,
Wheel mechanical characteristic when different hinge set width,
The wheel mechanical characteristic of different hinge set numbers；
S54, car wheel structure parameter improvement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810407188.XA CN108416178A (en) | 2018-05-02 | 2018-05-02 | A kind of mechanical elastic vehicle wheel Design of Structural parameters method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810407188.XA CN108416178A (en) | 2018-05-02 | 2018-05-02 | A kind of mechanical elastic vehicle wheel Design of Structural parameters method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108416178A true CN108416178A (en) | 2018-08-17 |
Family
ID=63137445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810407188.XA Pending CN108416178A (en) | 2018-05-02 | 2018-05-02 | A kind of mechanical elastic vehicle wheel Design of Structural parameters method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108416178A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109284539A (en) * | 2018-08-30 | 2019-01-29 | 沈阳云仿科技有限公司 | U-shaped bellows is hydraulic or gas pressure compacting die size and process parameter optimizing algorithm |
| CN110287629A (en) * | 2019-07-01 | 2019-09-27 | 国网重庆市电力公司电力科学研究院 | Determine computer installation, the device and method of high pressure basin-type insulator structure parameter |
| CN111950204A (en) * | 2020-08-13 | 2020-11-17 | 一汽解放汽车有限公司 | Hinge structure optimization method and device, computer equipment and storage medium |
| CN112115560A (en) * | 2020-08-31 | 2020-12-22 | 南京航空航天大学 | Light-weight design method for mechanical elastic wheel snap ring |
| CN113378935A (en) * | 2021-06-11 | 2021-09-10 | 中国石油大学(华东) | Intelligent olfactory sensation identification method for gas |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104778313A (en) * | 2015-03-27 | 2015-07-15 | 江苏大学 | Tire fatigue life evaluation and prediction method |
| CN105512424A (en) * | 2015-12-22 | 2016-04-20 | 湖南大学 | Method for obtaining engineering machinery tyre vertical characteristic parameters based on pulse test |
-
2018
- 2018-05-02 CN CN201810407188.XA patent/CN108416178A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104778313A (en) * | 2015-03-27 | 2015-07-15 | 江苏大学 | Tire fatigue life evaluation and prediction method |
| CN105512424A (en) * | 2015-12-22 | 2016-04-20 | 湖南大学 | Method for obtaining engineering machinery tyre vertical characteristic parameters based on pulse test |
Non-Patent Citations (4)
| Title |
|---|
| 卢昊: "高速列车车轮的疲劳可靠性灵敏度分析及可靠性稳健设计", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
| 张彬彬: "拓扑变化对新型机械弹性车轮力学性能的影响研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
| 杨甲沛: "基于自适应学习速率的改进型BP算法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 谢庆生等: "《机械工程中的神经网络方法》", 31 March 2003, 机械工业出版社 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109284539A (en) * | 2018-08-30 | 2019-01-29 | 沈阳云仿科技有限公司 | U-shaped bellows is hydraulic or gas pressure compacting die size and process parameter optimizing algorithm |
| CN109284539B (en) * | 2018-08-30 | 2022-11-04 | 沈阳云仿科技有限公司 | Method for optimizing size and technological parameters of hydraulic or pneumatic forming die of U-shaped corrugated pipe |
| CN110287629A (en) * | 2019-07-01 | 2019-09-27 | 国网重庆市电力公司电力科学研究院 | Determine computer installation, the device and method of high pressure basin-type insulator structure parameter |
| CN110287629B (en) * | 2019-07-01 | 2022-08-09 | 国网重庆市电力公司电力科学研究院 | Computer device, equipment and method for determining structural parameters of high-voltage basin-type insulator |
| CN111950204A (en) * | 2020-08-13 | 2020-11-17 | 一汽解放汽车有限公司 | Hinge structure optimization method and device, computer equipment and storage medium |
| CN111950204B (en) * | 2020-08-13 | 2022-04-19 | 一汽解放汽车有限公司 | Hinge structure optimization method and device, computer equipment and storage medium |
| CN112115560A (en) * | 2020-08-31 | 2020-12-22 | 南京航空航天大学 | Light-weight design method for mechanical elastic wheel snap ring |
| CN112115560B (en) * | 2020-08-31 | 2024-09-20 | 南京航空航天大学 | Mechanical elastic wheel snap ring lightweight design method |
| CN113378935A (en) * | 2021-06-11 | 2021-09-10 | 中国石油大学(华东) | Intelligent olfactory sensation identification method for gas |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108416178A (en) | A kind of mechanical elastic vehicle wheel Design of Structural parameters method | |
| CN103226741B (en) | Public supply mains tube explosion prediction method | |
| CN102682345B (en) | Based on the traffic flow forecasting method of two variable optimal learning rate Fast Learning neural network | |
| CN106920008A (en) | A kind of wind power forecasting method based on Modified particle swarm optimization BP neural network | |
| CN106777866B (en) | Energy-saving consumption-reducing-oriented modeling and optimizing method for high-sulfur-content natural gas purification process | |
| CN106600059A (en) | Intelligent power grid short-term load predication method based on improved RBF neural network | |
| CN109334378B (en) | Vehicle ISD suspension active control method based on single neuron PID control | |
| CN105046326B (en) | Pumping unit parameter optimization method based on function figure pivot analysis | |
| CN114217524A (en) | Power grid real-time self-adaptive decision-making method based on deep reinforcement learning | |
| CN113489015B (en) | Multi-time-scale reactive voltage control method for power distribution network based on reinforcement learning | |
| CN105354363A (en) | Fluctuation wind speed prediction method based on extreme learning machine | |
| CN107728478A (en) | Fuel cell excess oxygen coefficient network response surface method | |
| CN105243259A (en) | Extreme learning machine based rapid prediction method for fluctuating wind speed | |
| CN106951960A (en) | A kind of learning method of neutral net and the neutral net | |
| CN107451651A (en) | A kind of driving fatigue detection method of the H ELM based on particle group optimizing | |
| CN103793887A (en) | Short-term electrical load on-line predicting method based on self-adaptation enhancing algorithm | |
| CN112615364A (en) | Novel wide-area intelligent cooperative control method for power grid stability control device | |
| CN115689001A (en) | Short-term load prediction method based on pattern matching | |
| CN103559541A (en) | Back propagation method for out-of-order data stream in big data | |
| CN107563518A (en) | A kind of learning method of the extreme learning machine based on social force model colony optimization algorithm | |
| CN101546389A (en) | Primary direction neural network system | |
| CN104182854A (en) | Mixed energy consumption measuring method for enterprise energy management system | |
| CN110544124A (en) | waste mobile phone pricing method based on fuzzy neural network | |
| CN112785058B (en) | Water quality prediction method based on multi-source transfer learning | |
| CN101540504A (en) | Current analytical device and method on basis of step-length variable neural network |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180817 |
|
| RJ01 | Rejection of invention patent application after publication |