CN103761429A - Milling workpiece surface roughness predicting method - Google Patents
Milling workpiece surface roughness predicting method Download PDFInfo
- Publication number
- CN103761429A CN103761429A CN201410011258.1A CN201410011258A CN103761429A CN 103761429 A CN103761429 A CN 103761429A CN 201410011258 A CN201410011258 A CN 201410011258A CN 103761429 A CN103761429 A CN 103761429A
- Authority
- CN
- China
- Prior art keywords
- particle
- value
- surface roughness
- max
- milling
- 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
Images
Abstract
The invention belongs to the technical field of machining process and relates to a milling workpiece surface roughness predicting method. The method includes the steps of firstly, performing a material milling experiment and collecting and processing experiment data; secondly, on the basis of a particle swarm optimization least squares support vector machine algorithm, searching for the optimal parameters for building a surface roughness predicting model; thirdly, building the surface roughness predicting model, and predicting the corresponding workpiece surface roughness values under different milling conditions. The method has the advantages the method is fast in convergence, high in global optimization capability, high in prediction precision under a small sample condition, and high in generalization ability, high prediction precision can be obtained through few experiments, machining time can be reduced, cost can be lowered, machining efficiency and surface quality can be increased effectively, and scientific theoretical basis is provided for further formulating and optimizing the milling parameter combination for actual production.
Description
Technical field
The invention belongs to mechanical processing technique technical field, relate to a kind of Forecasting Methodology of Milling Process workpiece surface roughness.
Background technology
Metal cutting processing is to utilize cutter to cut metal unnecessary on workpiece blank, thereby obtain the job operation of the engineering goods that meet certain requirements, although a lot of new methods have appearred in metal manufacture field in recent decades, cut remains in machine-building the most substantially, the most general processing mode.In cut, surfaceness is that the important technology that carries out Element Design one of requires, and is also the important indicator of weighing workpiece crudy simultaneously.Surfaceness has a great impact for the fatigue strength of workpiece, contact stiffness, decay resistance etc.Therefore, before actual cut processing, according to factors such as cutting parameters, processing work surfaceness is predicted and not only can be reduced process time, reduce costs, and can also effectively improve working (machining) efficiency and surface quality actual production practice to be had to major application and be worth.
The main methods such as theoretical analysis, regretional analysis, neural network that adopt of Milling Process workpiece surface roughness prediction at present.Theoretical analysis method is mainly predicted by the formation mechanism effects on surface roughness of analyzing surfaceness in milling process, but working angles has complicacy and uncertainty, and the forecast model of setting up can not all be considered the impact of all factors, when setting up model, conventionally actual process is simplified, predicted the outcome and have larger error with real surface roughness value.The main thought of regression analysis is the multinomial model of setting up a surfaceness and influence factor, then utilizes the regression coefficient of experimental data solving model to set up Roughness Model.Regression analysis not only can disclose the rule that affects of each factor effects on surface roughness, and can also predict and control according to regression equation effects on surface roughness when factors vary, but the generalization ability of this method is poor and precision of prediction need to be based upon on the basis of great many of experiments, in the requirement that is difficult to meet the prediction of Milling Process workpiece surface roughness aspect precision of prediction and generalization ability.Neural network is a kind of animal nerve network behavior feature of imitating, carry out the mathematical algorithm of distributed parallel information processing, while adopting this algorithm predicts surfaceness, have that learning ability is strong, parallel processing capability and the advantage such as robustness is good, still also exist the shortcomings such as network internal unit interrogatory is true, training time length, structural knowledge beyond expression of words.
Summary of the invention
The object of this invention is to provide a kind of Forecasting Methodology of new Milling Process workpiece surface roughness, it can improve precision of prediction and the generalization ability of workpiece surface roughness forecast model in Milling Processes, thereby surfaceness corresponding under different milling conditions is predicted.
Technical solution of the present invention flow process as shown in Figure 1, its main thought is to utilize least square method supporting vector machine algorithm can solve preferably high dimension, local minimum, small sample problem, by a small amount of experiment, can obtain the advantage of higher precision of prediction and generalization ability, set up Milling Process workpiece surface roughness forecast model, the surface roughness value that different Milling Parameters are corresponding is predicted, but setting up in forecast model process, penalty factor in least square method supporting vector machine algorithm and kernel functional parameter σ have a significant impact the precision of forecasting model tool of setting up, therefore before forecast model, first introduce the least square method supporting vector machine of particle group optimizing shown in Fig. 2 (PSO-LSSVM) method and carry out iteration optimization setting up, find optimum penalty factor and kernel functional parameter σ, then utilize the parameter after optimizing to set up Roughness Model, Milling Process workpiece surface roughness is predicted, concrete steps are as follows:
Step 1: the acquisition and processing of the experiment of material Milling Process and experimental data;
1. choose processing work material, determine the processing factors that affects Milling Process workpiece surface roughness, formulate suitable experimental program and test, and measure corresponding surface roughness value;
2. record different Milling Parameters and corresponding surface roughness value, and experimental data is normalized as the training sample of setting up forecast model.
Step 2: the optimized parameter of seeking to set up Roughness Model based on particle group optimizing least square method supporting vector machine algorithm;
1. initialization particle population.Set the parameters such as iterations, particle number, and produce at random initial position X (0) and the speed V (0) of one group of particle;
2. according to formula (1), calculate the fitness fit of particle X (i)
k(i)
Fit in formula
k(i) be the fitness value of k particle of population after the i time iteration,
for the predicted value obtaining by least square method supporting vector machine algorithm, y
jfor actual value, n is number of samples;
3. the individual optimal value of new particle more.By particle fitness value fit
k(i) with the fitness value p of current individual optimal solution
ibestrelatively, if fit
k(i) be less than p
ibest, with this particle, replace current individual optimal value;
4. colony's optimal value of new particle more.By particle fitness value fit
k(i) with the optimum solution fitness value g of current colony
bestrelatively, if fit
k(i) value is less than g
best, with this particle, replace current colony optimal value;
5. upgrade position X (i) and the speed V (i) of weight factor w and particle.According to formula (2), (3), (4), upgrade position X (i)=(x of weight factor w and particle
1(i), x
2(i) ... x
k) and speed V (i)=(v (i)
1(i), v
2(i) ... v
k(i)), if X (i) is >X
max, X (i)=X so
max; If X (i) is <X
max, X (i)=X so
max; If V (i) is >V
max, V (i)=V so
max; If V (i) is <V
min, V (i)=V so
min.
w=w
min+(iter
max-iter)*(w
max-w
min)/iter
max （2）
v(i)=w*v(i-1)+c
1*rand*(p
best(i-1)-x(i-1))+c
2*rand*(g
best(i-1)-x(i-1)) （3）
x(i)=x(i-1)+v(i) （4）
In formula (2), w
minfor weight factor minimum value, w
maxfor weight factor maximal value, iter
maxfor maximum iteration time, iter is current iteration number of times; In formula (3) and (4), v (i), v (i-1), x (i), position and the speed of particle when x (i-1) represents respectively the i time iteration and (i-1) inferior iteration, p
ibest(i-1) be the fitness value of current individual optimal solution, g
best(i-1) be the fitness value of current group optimal solution, rand is the random number between 0 to 1, c
1, c
2for the study factor;
6. judge whether to reach iterations, if reached, stop iterative computation and export population optimal particle value, otherwise return to step 2..
Step 3: set up Roughness Model, and processing work roughness value corresponding under different milling conditions is predicted;
1. global optimum's particle value step 2 being obtained is assigned to respectively penalty factor and kernel functional parameter σ, utilizes training sample to set up corresponding Prediction Model for Surface Roughness in Milling;
2. by the Milling Parameters input model of needs prediction, can obtain corresponding Milling Process workpiece surface roughness value.
Effect of the present invention and benefit are: the present invention joins together particle cluster algorithm and least square method supporting vector machine algorithm to predict for Milling Process workpiece surface roughness, making this inventive method when carrying out Prediction of Surface Roughness, both have particle cluster algorithm is easy to realize, fast convergence rate, the advantages such as global optimization ability is strong, also had least square method supporting vector machine algorithm precision of prediction under condition of small sample concurrently high simultaneously, the advantage that generalization ability is strong, can obtain higher precision of prediction and generalization ability by a small amount of experiment, realized the high-precision forecast of the different machining condition lower surface of Milling Process roughness, in actual production, not only can reduce process time, reduce costs, effectively improve working (machining) efficiency and surface quality, simultaneously also for further formulate and optimize for the production of Milling Parameters combination the theoretical foundation of science is provided.
Accompanying drawing explanation
Accompanying drawing 1 is the Forecasting Methodology process schematic diagram of Milling Process workpiece surface roughness.
Accompanying drawing 2 is particle group optimizing least square method supporting vector machine algorithm flow charts.
Accompanying drawing 3 is fitness value iterative evolution procedure charts.
Accompanying drawing 4 is least square method supporting vector machine structural drawing.
Accompanying drawing 5 is training set sample predicted value and actual value comparison diagram.
Accompanying drawing 6 is test set sample predicted value and actual value comparison diagram.
Embodiment
The present invention is processed as example with flat surface of aluminum alloy end mill, choosing the speed of mainshaft, the amount of feeding and cutting depth is the factor that affects Milling Process workpiece surface roughness, set up aluminium alloy milling surface roughness value forecast model, and surface roughness value corresponding to different Milling Parameters predicted.Below in conjunction with technical scheme of the present invention and accompanying drawing, describe specific embodiment of the invention step in detail.
Step 1: collection and the processing of the experiment of material Milling Process and experimental data.
1. choosing aluminium alloy is milling of materials, selecting the speed of mainshaft, the amount of feeding and cutting depth in Milling Process is the influence factor of setting up processing work Roughness Model, change the speed of mainshaft, the amount of feeding and cutting depth and on milling machine, carry out the experiment of aluminium alloy Milling Process, and measure corresponding surface roughness value.Wherein each processing factors level is as shown in table 1;
Table 1 Milling Process factor and level
2. record 48 groups of Milling Parameters and corresponding workpiece surface roughness value, and according to formula (5), experimental data be normalized,
In formula x and
value before being respectively normalization and after normalization; x
minand x
maxbe respectively maximal value and the minimum value of sample.
Step 2: the optimized parameter of seeking to set up Roughness Model based on particle group optimizing least square method supporting vector machine algorithm.
1. initialization particle population.Setting particle dimension is 2, and population size is 20, study factor c
1=c
2=2, maximum iteration time iter
max=100, particle maximum speed value v
max=20, particle minimum speed value v
min=-20, weight factor maximal value, minimum value are respectively w
max=0.9, w
min=0.4, the penalty factor region of search is set as [0,1000], and the kernel functional parameter σ region of search is set as [0,2], and produces at random initial position X (0) and the initial velocity matrix V (0) of particle;
2. choose the kernel function that formula (6) radial basis function (RBF function) is least square method supporting vector machine algorithm, and according to formula (1), calculate the fitness fit of particle X (i)
k(i),
3. by particle fitness value fit
k(i) with the fitness value p of current individual optimal solution
ibestrelatively, if fit
k(i) be less than p
ibest, with this particle, replace current individual optimal value;
4. by particle adaptive value fit
k(i) with the fitness value g of current group optimal solution
bestrelatively, if fit
k(i) value is less than g
best, with this particle, replace current colony optimal value;
5. according to formula (2), (3), (4), upgrade position X (i)=(x of weight factor w and particle
1(i), x
2(i) ... x
k) and speed V (i)=(v (i)
1(i), v
2(i) ... v
k(i)), if V (i) is >V
max, V (i)=V so
max; If V (i) is <V
min, V (i)=V so
min; If X (i) is >X
max, X (i)=X so
max; If X (i) is <X
max, X (i)=X so
max;
6. judge whether iterations reaches 100 times, if do not reached, return to step and 2. continue iteration.After 100 iteration, obtain optimal particle value X=(0.1378,520.6806), Fig. 3 is the evolution curve of iteration population average fitness value and optimum individual fitness value each time.
Step 3: after utilizing optimization, parameter is set up forecast model, and surface roughness value corresponding to random Milling Parameters predicted.
1. by step 2, can obtain optimum punishment parameters C=520.6806, optimum kernel functional parameter σ=0.1378.Then utilize the Optimal Parameters obtaining, take Milling Parameters in training sample as input, to measure the respective surfaces roughness value obtaining as output, according to the structural drawing of least square method supporting vector machine shown in Fig. 4, forecast model is trained, set up corresponding aluminium alloy Milling Process workpiece surface roughness forecast model and obtain the predicted value that training sample is corresponding.Training set sample surface roughness predicted value and actual measured value contrast as shown in Figure 5, and Prediction of Surface Roughness value and actual value that the forecast model of setting up as shown in Figure 5 obtains are close, and precision of prediction is higher.Can obtain as calculated training set sample precision of prediction is 99.4%;
2. surface roughness value corresponding to random Milling Parameters predicted.In random option table 2,24 groups of Milling Parameters, as forecast sample, by the Roughness Model that after the Milling Parameters normalization in sample, input is set up, can obtain the workpiece surface roughness predicted value that different Milling Parameters are corresponding.Can be for other non-training sample Milling Parameters by table 2, the Milling Process workpiece surface roughness forecast model predicated error mean value that this method is set up is 3.26%, and the known forecast model of setting up by the present invention can carry out accurately predicting to aluminium alloy Milling Process surface roughness value under different Milling Parameters.
Table 2 forecast sample predicts the outcome
The surface roughness value that Fig. 6 obtains actual forecast sample Milling Process and the model prediction of foundation obtain surfaceness and compare, shown more intuitively the advantage of this method aspect precision of prediction and generalization ability, the model that further illustrates this method foundation not only can be predicted the surface roughness value that training sample is corresponding, and can carry out accurately predicting to the Milling Parameters in other non-training sample.
Simultaneously in order to prove that the present invention is in feasibility and high precision aspect Milling Process Prediction of Surface Roughness, table 3 is by consensus forecast precision of the present invention and document [Prakasvudhisarn, C.Kunnapapdeelert, S. & Yenradee, P.Optimal cutting condition determination for desired surface roughness in end milling.International Journal of Advanced Manufacturing Technology, 2009, 41 (5), 440 – 451.] precision of prediction of other surfaceness method that obtains of retrieval carried out contrast precision of prediction and contrasted, further verified the advantage of the present invention aspect Prediction of Surface Roughness.Wherein consensus forecast precision calculates according to formula (7).
In formula
prediction of Surface Roughness value, R
aisurface finish measurement value, n is sample set sample number.
Table 3 the present invention and the contrast of additive method precision of prediction
Claims (4)
1. a Forecasting Methodology for Milling Process workpiece surface roughness, comprises experimental data acquisition and processing, parameter optimization and sets up forecast model three parts, it is characterized in that:
A. when carrying out parameter optimization, use seeks to set up the optimized parameter of Roughness Model based on particle group optimizing least square method supporting vector machine algorithm;
B. utilize the parameter after optimizing to set up Roughness Model, and processing work roughness value corresponding under different milling conditions is predicted.
2. the Forecasting Methodology of a kind of Milling Process workpiece surface roughness according to claim 1, is characterized in that: at the algorithm of particle group optimizing least square method supporting vector machine described in a. step, comprise the following steps:
1. initialization particle population; Set the parameters such as iterations, particle number, and produce at random initial position X (0) and the speed V (0) of one group of particle;
2. according to formula
calculate the fitness fit of particle X (i)
k(i), fit in formula
k(i) be the fitness value of k particle of population after the i time iteration,
for the predicted value obtaining by least square method supporting vector machine algorithm, y
jfor actual value, n is number of samples;
3. the individual optimal value of new particle more, by particle fitness value fit
k(i) with the fitness value p of current individual optimal solution
ibestrelatively, if fit
k(i) be less than p
ibest, with this particle, replace current individual optimal value;
4. colony's optimal value of new particle more, by particle fitness value fit
k(i) with the optimum solution fitness value g of current colony
bestrelatively, if fit
k(i) value is less than g
best, with this particle, replace current colony optimal value;
5. upgrade position X (i)=(x of weight factor w and particle
1(i), x
2(i) ... x
k) and speed V (i)=(v (i)
1(i), v
2(i) ... v
k(i)), if X (i) is >X
max, X (i)=X so
max; If X (i) is <X
max, X (i)=X so
max; If V (i) is >V
max, V (i)=V so
max; If V (i) is <V
min, V (i)=V so
min;
6. judge whether to reach iterations, if reached, stop iterative computation and export population optimal particle value, otherwise return to step 2..
3. according to the Forecasting Methodology of a kind of Milling Process workpiece surface roughness described in claim 2, it is characterized in that: described particle group optimizing least square method supporting vector machine algorithm is middle weight factor w, particle rapidity V (i)=(v 5.
1(i), v
2(i) ... v
k) and particle position X (i)=(x (i)
1(i), x
2(i) ... x
k(i)) respectively by formula w=w
min+ (iter
max-iter) * (w
max-w
min)/iter
max,
v(i)=w*v(i-1)+c
1*rand*(p
best(i-1)-x(i-1))+c
2*rand*(g
best(i-1)-x(i-1))
X (i)=(x
1(i), x
2(i) ... x
k(i)) calculate w in formula
minfor weight factor minimum value, w
maxfor weight factor maximal value, iter
maxfor maximum iteration time, iter is current iteration number of times, speed and the position of particle when v (i), v (i-1), x (i-1), x (i) represent respectively the i time iteration and (i-1) inferior iteration, p
ibest(i-1) be the fitness value of current individual optimal solution, g
best(i-1) be the fitness value of current group optimal solution, rand is the random number between 0 to 1, c
1, c
2for the study factor.
4. the Forecasting Methodology of a kind of Milling Process workpiece surface roughness according to claim 1, it is characterized in that: the parameter in claim 1 after b. step utilization optimization is set up global optimum's particle value that Roughness Model need to obtain optimization and is assigned to respectively penalty factor and kernel functional parameter σ, utilizes training sample to set up corresponding Prediction Model for Surface Roughness in Milling.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410011258.1A CN103761429A (en) | 2014-01-10 | 2014-01-10 | Milling workpiece surface roughness predicting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410011258.1A CN103761429A (en) | 2014-01-10 | 2014-01-10 | Milling workpiece surface roughness predicting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103761429A true CN103761429A (en) | 2014-04-30 |
Family
ID=50528665
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410011258.1A Pending CN103761429A (en) | 2014-01-10 | 2014-01-10 | Milling workpiece surface roughness predicting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103761429A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104933310A (en) * | 2015-06-19 | 2015-09-23 | 河海大学 | Method for predicting membrane pollution tendency in membrane distilled water processing system on the basis of GA-LSSVM (Genetic Algorithm- Least Squares Support Vector Machine) model |
| CN105269402A (en) * | 2015-10-13 | 2016-01-27 | 南京航空航天大学 | Method for predicating surface roughness of titanium alloy material based on milling |
| CN105956235A (en) * | 2016-04-20 | 2016-09-21 | 杭州电子科技大学 | Optimum design method for ultrasonic machining special cutter based on SVR-PSO |
| CN106407669A (en) * | 2016-09-07 | 2017-02-15 | 江苏大学 | Prediction method of cut surface roughness |
| CN108563866A (en) * | 2018-04-13 | 2018-09-21 | 贵州大学 | A kind of mould steel milling Prediction of Surface Roughness system based on GA-ELM algorithms |
| CN109255182A (en) * | 2018-09-09 | 2019-01-22 | 浙江工业大学 | A kind of hard brittle material technology-parameter predictive model and its Multipurpose Optimal Method |
| CN109543329A (en) * | 2018-11-30 | 2019-03-29 | 厦门大学 | A kind of face cutter Prediction Method of Milling Forces of combination SVM |
| CN110348075A (en) * | 2019-06-20 | 2019-10-18 | 湖南科技大学 | A kind of grinding surface roughness prediction technique based on improvement algorithm of support vector machine |
| CN110597060A (en) * | 2019-09-17 | 2019-12-20 | 西北工业大学 | Thin-wall part side milling surface roughness prediction method based on monitoring acceleration |
| CN111859566A (en) * | 2020-07-17 | 2020-10-30 | 重庆大学 | Surface roughness stabilizing method based on digital twinning |
| WO2021128577A1 (en) * | 2019-12-24 | 2021-07-01 | 大连理工大学 | Sdae-dbn algorithm-based online prediction method for surface roughness of part |
| CN113688534A (en) * | 2021-09-02 | 2021-11-23 | 江苏师范大学 | Research method for searching optimal milling parameter based on multi-feature fusion model |
| CN113704922A (en) * | 2021-09-01 | 2021-11-26 | 江苏师范大学 | Method for predicting surface roughness based on sound vibration and texture features |
| CN113919101A (en) * | 2021-10-29 | 2022-01-11 | 哈尔滨工业大学 | Ball head grinding wheel grinding process parameter optimization method based on response surface method and particle population optimization algorithm |
| CN114139772A (en) * | 2021-11-12 | 2022-03-04 | 江苏师范大学 | Method for predicting surface quality of workpiece based on optimized generalized regression neural network |
| CN114453630A (en) * | 2022-01-20 | 2022-05-10 | 湖北文理学院 | Method and device for controlling machine tool to mill non-stick tool, electronic equipment and storage medium |
| CN116578832A (en) * | 2023-07-13 | 2023-08-11 | 兰州理工大学 | Device for predicting surface roughness of machined part |
-
2014
- 2014-01-10 CN CN201410011258.1A patent/CN103761429A/en active Pending
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104933310A (en) * | 2015-06-19 | 2015-09-23 | 河海大学 | Method for predicting membrane pollution tendency in membrane distilled water processing system on the basis of GA-LSSVM (Genetic Algorithm- Least Squares Support Vector Machine) model |
| CN105269402A (en) * | 2015-10-13 | 2016-01-27 | 南京航空航天大学 | Method for predicating surface roughness of titanium alloy material based on milling |
| CN105956235A (en) * | 2016-04-20 | 2016-09-21 | 杭州电子科技大学 | Optimum design method for ultrasonic machining special cutter based on SVR-PSO |
| CN105956235B (en) * | 2016-04-20 | 2019-03-08 | 杭州电子科技大学 | Ultrasonic machining special type knife optimum design method based on SVR-PSO |
| CN106407669A (en) * | 2016-09-07 | 2017-02-15 | 江苏大学 | Prediction method of cut surface roughness |
| CN108563866A (en) * | 2018-04-13 | 2018-09-21 | 贵州大学 | A kind of mould steel milling Prediction of Surface Roughness system based on GA-ELM algorithms |
| CN109255182A (en) * | 2018-09-09 | 2019-01-22 | 浙江工业大学 | A kind of hard brittle material technology-parameter predictive model and its Multipurpose Optimal Method |
| CN109543329B (en) * | 2018-11-30 | 2022-10-14 | 厦门大学 | SVM (support vector machine) -combined end mill milling force prediction method |
| CN109543329A (en) * | 2018-11-30 | 2019-03-29 | 厦门大学 | A kind of face cutter Prediction Method of Milling Forces of combination SVM |
| CN110348075A (en) * | 2019-06-20 | 2019-10-18 | 湖南科技大学 | A kind of grinding surface roughness prediction technique based on improvement algorithm of support vector machine |
| CN110597060A (en) * | 2019-09-17 | 2019-12-20 | 西北工业大学 | Thin-wall part side milling surface roughness prediction method based on monitoring acceleration |
| CN110597060B (en) * | 2019-09-17 | 2022-04-15 | 西北工业大学 | Thin-wall part side milling surface roughness prediction method based on monitoring acceleration |
| WO2021128577A1 (en) * | 2019-12-24 | 2021-07-01 | 大连理工大学 | Sdae-dbn algorithm-based online prediction method for surface roughness of part |
| CN111859566A (en) * | 2020-07-17 | 2020-10-30 | 重庆大学 | Surface roughness stabilizing method based on digital twinning |
| CN111859566B (en) * | 2020-07-17 | 2023-11-17 | 重庆大学 | Digital twinning-based surface roughness stabilization method |
| CN113704922A (en) * | 2021-09-01 | 2021-11-26 | 江苏师范大学 | Method for predicting surface roughness based on sound vibration and texture features |
| CN113704922B (en) * | 2021-09-01 | 2024-02-02 | 江苏师范大学 | Method for predicting surface roughness based on sound vibration and texture characteristics |
| CN113688534A (en) * | 2021-09-02 | 2021-11-23 | 江苏师范大学 | Research method for searching optimal milling parameter based on multi-feature fusion model |
| CN113688534B (en) * | 2021-09-02 | 2024-04-05 | 苏州莱库航空装备科技有限公司 | Research method for searching optimal milling parameters based on multi-feature fusion model |
| CN113919101A (en) * | 2021-10-29 | 2022-01-11 | 哈尔滨工业大学 | Ball head grinding wheel grinding process parameter optimization method based on response surface method and particle population optimization algorithm |
| CN113919101B (en) * | 2021-10-29 | 2024-04-19 | 哈尔滨工业大学 | Ball grinding wheel grinding process parameter optimization method based on response surface method and particle population optimization algorithm |
| CN114139772B (en) * | 2021-11-12 | 2023-10-27 | 江苏师范大学 | Method for predicting workpiece surface quality based on optimized generalized regression neural network |
| CN114139772A (en) * | 2021-11-12 | 2022-03-04 | 江苏师范大学 | Method for predicting surface quality of workpiece based on optimized generalized regression neural network |
| CN114453630A (en) * | 2022-01-20 | 2022-05-10 | 湖北文理学院 | Method and device for controlling machine tool to mill non-stick tool, electronic equipment and storage medium |
| CN116578832A (en) * | 2023-07-13 | 2023-08-11 | 兰州理工大学 | Device for predicting surface roughness of machined part |
| CN116578832B (en) * | 2023-07-13 | 2023-09-12 | 兰州理工大学 | Device for predicting surface roughness of machined part |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103761429A (en) | Milling workpiece surface roughness predicting method | |
| CN101412196B (en) | Turning force prediction method based on cutting-tool angle and cutting amount parametric variation | |
| Li et al. | Multi-objective optimization of cutting parameters in sculptured parts machining based on neural network | |
| CN102880771B (en) | Method for predicting surface roughness of workpiece during high-speed cutting machining | |
| CN103761423B (en) | A kind of hot rolled plate microstructure and property prediction method based on PSO-ELM | |
| CN105160059A (en) | BP and GA based blade machining cutting quantity optimization selection method | |
| CN110609531A (en) | Workshop scheduling method based on digital twin | |
| CN104778378A (en) | Method for analyzing influence factors of production decline of oil and gas field | |
| CN105956235A (en) | Optimum design method for ultrasonic machining special cutter based on SVR-PSO | |
| CN105873703B (en) | The design method of machining condition in machining | |
| CN104375478A (en) | Method and device for online predicting and optimizing product quality in steel rolling production process | |
| Lu et al. | An effective ABC-SVM approach for surface roughness prediction in manufacturing processes | |
| CN105269402A (en) | Method for predicating surface roughness of titanium alloy material based on milling | |
| CN110728049A (en) | Combined prediction model establishing method for tool turning temperature variation mean value | |
| CN111721835A (en) | Intelligent monitoring method for grinding wheel state of hollow drill | |
| CN104318022A (en) | Method for predicting workpiece surface roughness and increasing cutting efficiency | |
| Jeet et al. | Multi-parametric optimization during drilling of aerospace alloy (UNS A97068) using hybrid RSM-GRA, GA and SA | |
| CN110509096A (en) | Workpiece surface roughness control method, device and numerically controlled processing equipment | |
| CN108520117A (en) | A method of obtaining the stability lobes diagram using approximate shceme method | |
| CN102930337A (en) | Prediction method for cutting amount in cutting machining | |
| CN107103129A (en) | The Forecasting Methodology of workpiece surface residual stress in a kind of machining | |
| Sredanović et al. | Optimization of cutting parameters for minimizing specific Cutting energy and maximizing productivity in turning of AISI 1045 steel | |
| Singh et al. | Parameters optimization for sustainable machining by using Taguchi method | |
| Yue et al. | Multi-objective optimization of machined surface integrity for hard turning process | |
| Ahmad et al. | Modelling and prediction of surface roughness and power consumption using parallel extreme learning machine based particle swarm optimization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140430 |
|
| RJ01 | Rejection of invention patent application after publication |