TWM607654U - Intelligent ultrasonic grinding and polishing aided system - Google Patents

Abstract

The model provides an intelligent ultrasonic assisted grinding and processing system, which includes a grinding machine, a database and a processor. The database records the plural processing data of the grinding machine. The processor includes a machining accuracy prediction module and a machining parameter optimization module. The machining accuracy prediction module receives the machining data from the database, and trains the machining data according to the interval-type fuzzy neural network, establishes a grinding prediction model, and generates surface grinding accuracy. The processing parameter optimization module calculates the best processing parameters corresponding to the surface grinding accuracy. The grinding machine grinds the workpiece according to the best processing parameters. In this way, the huge material and cost of trial and error method are effectively reduced, so that inexperienced operators can also grind workpieces with ideal grinding accuracy.

Description

Intelligent ultrasonic assisted grinding processing system

This model relates to a grinding processing system, in particular to an intelligent ultrasonic assisted grinding processing system.

In the existing grinding and polishing processing technology, the selection of processing materials, processing grinding rods, polishing tools and polishing materials will produce different processing accuracy, surface roughness and grinding and polishing time. Grinding and polishing processing mainly relies on personal experience to set processing parameters. If you want to grind and polish materials that have not been touched, you cannot set the processing parameters accurately.

It can be seen that there is currently a lack of a grinding processing system in the market that can set the expected surface roughness value to calculate the best processing parameters according to the needs of users, so the relevant industry is seeking its solution.

Therefore, the purpose of the present invention is to provide an intelligent ultrasonic-assisted grinding processing system, which establishes a grinding prediction model based on the previously recorded processing data to generate surface grinding accuracy, and calculates the best processing parameters corresponding to the surface grinding accuracy.

According to an embodiment of the structural aspect of the present invention, an intelligent ultrasonic-assisted grinding processing system is provided to predict the surface grinding accuracy of a workpiece after grinding. The intelligent ultrasonic-assisted grinding processing system includes a grinding machine, a database and a processor. The database signal is connected to the grinding machine and records the plural processing data of the grinding machine. The processor signal is connected to the grinding machine and the database, and includes a processing accuracy prediction module and a processing parameter optimization module. The processing accuracy prediction module receives these processing data from the database, and the processing accuracy prediction module trains these processing data and establishes a grinding prediction model based on the interval type 2 fuzzy neural network. The interval type 2 fuzzy neural network passes Dynamic clustering difference calculation unit is adjusted to produce surface polishing accuracy. The processing parameter optimization module signal is connected to the processing accuracy prediction module and receives the surface grinding accuracy. The processing parameter optimization module optimizes the processing data according to the optimization unit to calculate a plurality of optimal processing parameters corresponding to the surface grinding accuracy. The grinding machine grinds the workpiece according to these optimal processing parameters.

In this way, operators with no experience can also set the best processing parameters corresponding to the surface grinding accuracy according to the surface grinding accuracy to be achieved, and perform grinding or polishing treatment on the workpiece.

Other examples of the foregoing embodiment are as follows: the foregoing interval-type 2 fuzzy neural network includes a first layer, a second layer, a third layer, a fourth layer, and a fifth layer. These processing data are stored in the first layer. The second layer performs fuzzification operations on these processed data, and calculates the interval type-2 fuzzy set. The third layer performs cumulative multiplication on the interval type-2 fuzzy set. The fourth layer performs a reduction operation on the interval type 2 fuzzy set and the linear function weight, and calculates the type 1 fuzzy set. The fifth layer performs defuzzification operations on a fuzzy set, and calculates the surface grinding accuracy. The interval type 2 fuzzy set includes Gaussian mean value, Gaussian standard deviation and Gaussian displacement.

Other examples of the foregoing embodiment are as follows: the foregoing dynamic clustering differential calculation unit includes an initialization sub-module, an adaptive threshold calculation sub-module, a clustering sub-module, a mutation sub-module, an exchange sub-module, and a selection sub-module. The initialization sub-module encodes the Gaussian average, Gaussian standard deviation, Gaussian displacement, and linear function weights into one body, and the interval-type 2 fuzzy neural network further includes plural individuals. The adaptive threshold calculation sub-module, the signal is connected to the initialization sub-module, and the distance threshold and the adaptive threshold of each body are calculated, and the plural leaders of the plural groups are defined. The grouping sub-module signals are connected to the adaptive threshold calculation sub-module, and these individuals are divided into these groups according to the distance threshold and the adaptive threshold of each body. The mutation sub-module signal is connected to the grouping sub-modules, and a mutation vector is generated from one of the leaders and the best leader of these leaders according to the Levi flight strategy. The exchange sub-module signal is connected to the mutation sub-module, and the exchange sub-module performs exchange operations on the mutation vector and generates a test vector. Select the sub-module signal to connect to the exchange sub-module. The selected sub-module compares the test vector and the best leader and selects the one that retains the largest adaptive threshold to become the surface polishing accuracy.

Other examples of the foregoing embodiment are as follows: the foregoing optimization unit calculates the complex processing parameters and surface polishing accuracy of each processing data to calculate these optimal processing parameters corresponding to the surface polishing accuracy.

Other examples of the foregoing embodiment are as follows: the foregoing processor further includes an update data collection module. The updated data collection module signals are connected to the processing accuracy prediction module and the processing parameter optimization module, and the updated data collection module collects surface grinding accuracy and these optimal processing parameters to form an updated data set. The machining accuracy prediction module updates the grinding prediction model based on the updated data set formed by the updated data collection module to generate an updated prediction model.

Please refer to Figures 1 to 3 together. Fig. 1 is a block diagram of the intelligent ultrasonic-assisted grinding and processing system 100 of the first embodiment of the present invention; Fig. 2 is a block diagram of the intelligent ultrasonic-assisted grinding and processing system 100 in Fig. 1 The schematic diagram of the similar neural network 320; and FIG. 3 is a block diagram of the dynamic grouping difference calculation unit 330 of the intelligent ultrasonic-assisted grinding processing system 100 of FIG. 1. The intelligent ultrasonic assisted grinding processing system 100 is used to predict the surface grinding accuracy Y of the workpiece after grinding, and includes a grinding machine 10, a database 20 and a processor 30. Among them, the signal of the database 20 is connected to the grinding machine 10, and the plural processing data of the grinding machine 10 are recorded. The processor 30 signals to connect the grinding machine 10 and the database 20. Specifically, the grinding machine 10 may be a three-axis CNC milling machine, the database 20 may be a memory, and the processor 30 may be a central processing unit (CPU), but the present invention is not limited to this.

The processor 30 includes a processing accuracy prediction module 310 and a processing parameter optimization module 340. The processing accuracy prediction module 310 receives the processing data of the database 20, and trains the processing data and establishes a grinding prediction model according to the interval type 2 fuzzy neural network 320. The interval type 2 fuzzy neural network 320 is calculated by dynamic clustering and difference calculation. The unit 330 is adjusted to produce a surface polishing accuracy Y. The processing parameter optimization module 340 signals the processing accuracy prediction module 310 and receives the surface grinding accuracy Y. Specifically, processing data includes multiple processing parameters and corresponding accuracy values. Processing parameters include processing material, diamond number, linear speed, feed speed, cutting depth, cutting width and ultrasonic power, but this new model is not limited to this .

The interval type 2 fuzzy neural network 320 includes a first layer Layer1, a second layer Layer2, a third layer Layer3, a fourth layer Layer4, and a fifth layer Layer5. The first layer Layer1 stores the processing data, and the processing data is sent to the second layer Layer2 as the input values X ₁ ~ X _{n of the} interval type 2 fuzzy neural network 320; the second layer Layer2 performs the fuzzy calculation on the processing data, and Calculate the interval type 2 fuzzy set; the third layer Layer 3 performs cumulative multiplication operation on the interval type 2 fuzzy set; the fourth layer Layer 4 performs the order reduction operation on the interval type 2 fuzzy set and the linear function weight, and calculates the type 1 fuzzy set; The fifth layer, Layer5, performs defuzzification operations on the first-type fuzzy set and calculates the surface polishing accuracy Y. The interval-type second-type fuzzy set includes Gaussian average, Gaussian standard deviation and Gaussian displacement.

The machining accuracy prediction module 310 further adjusts the parameters in the interval type-2 fuzzy neural network 320 through the dynamic clustering difference calculation unit 330. Parameters include Gaussian mean, Gaussian standard deviation, Gaussian displacement and linear function weight. The dynamic grouping difference calculation unit 330 includes an initialization sub-module 331, an adaptive threshold calculation sub-module 332, a grouping sub-module 333, a mutation sub-module 334, an exchange sub-module 335, and a selection sub-module 336.

The initialization sub-module 331 encodes the Gaussian mean value, Gaussian standard deviation, Gaussian displacement, and linear function weight into one body, where the interval-type 2 fuzzy neural network 320 further includes plural individuals.

，然後計算距離閥值(

)及適應閥值(

)，其計算規則如式(1)到式(4)所示：

尚未被分群              (1)；

(2)；

尚未被分群              (3)；

(4)； 其中D代表維度，NP為個體總數，

為組別，

則代表第

群的領袖，

代表當前的個體，NI代表當前個體中群組編號為0的個體總數。 The adaptive threshold calculation sub-module 332 is signaled to connect to the initialization sub-module 331, and the adaptive threshold calculation sub-module 332 calculates the distance threshold and the adaptive threshold of each body, and defines the plural leaders of the plural groups. In detail, the adaptation threshold calculation sub-module 332 sets the initial value of the group numbers of these individuals to 0, and sorts all individuals according to their adaptation thresholds. After sorting, the individual with the highest adaptation threshold is set as the leader from the individuals whose group number is 0, and the group number is updated to

, And then calculate the distance threshold (

) And adaptation threshold (

), the calculation rules are as shown in formula (1) to formula (4):

Not yet grouped (1);

(2);

Not yet grouped (3);

(4); where D represents the dimension, NP is the total number of individuals,

Is the group,

Represents the first

The leader of the group,

Represents the current individual, and NI represents the total number of individuals whose group number is 0 in the current individual.

)及適應值差(

)，並判斷未分群的個體之群體編號，距離差(

)及適應值差(

)的計算規則如式(5)、式(6)所示：

(5)；

(6)； 若

且

，則表示個體

與第

群的領袖

是相似的，將

的群組編號更新為

，所有個體皆有組別後，分群子模組333終止執行。 The grouping sub-module 333 signals the adaptive threshold calculation sub-module 332, and divides the individuals into these groups according to the distance threshold and the adaptive threshold of each body. Specifically, the grouping submodule 333 calculates the distance difference between the individual whose group number is 0 and each leader (

) And fitness difference (

), and judge the group number of the ungrouped individuals, and the distance difference (

) And fitness difference (

The calculation rules of) are shown in formulas (5) and (6):

(5);

(6); if

And

, It means the individual

And

Leader of the group

Is similar, will

Updated to

After all individuals have groups, the grouping sub-module 333 terminates execution.

(7)；

(8)；

(9)；

(10)； 其中

為突變向量，

為最佳領袖，

為所有群組中隨機選取的其中一領袖，F為突變權重因子，

為萊維飛行策略，

為萊維飛行策略之飛行指數，

和

為具有均值

與

的常態隨機分布。突變子模組334藉由結合萊維飛行策略，將最佳領袖設為基準向量，並加入兩個隨機個體的差異向量，使得突變後的突變向量圍繞著最好的個體。 The mutation sub-module 334 is connected to the grouping sub-module 333 by a signal, and generates a mutation vector from one of the leaders and the best leader of these leaders according to the Levi flight strategy. In detail, the mutation rules of the mutation sub-module 334 combined with Levi's flight strategy are shown in formula (7), formula (8), formula (9), and formula (10):

(7);

(8);

(9);

(10); where

Is the mutation vector,

As the best leader,

Is one of the leaders randomly selected in all groups, F is the mutation weighting factor,

For Levi’s flight strategy,

Is the flight index of Levi's flight strategy,

with

Mean

versus

The normal random distribution. The mutation sub-module 334 combines the Levi flight strategy to set the best leader as the reference vector and adds the difference vector of two random individuals, so that the mutation vector after the mutation surrounds the best individual.

(11)； 其中

為試驗向量；

為突變向量；

為目標向量；

為每個維度對應的隨機值，其值為0到1之間的亂數；CR為交換率。若交換率CR愈大，則試驗向量與突變向量的相似度愈高；若交換率CR愈小，則試驗向量與突變向量的相似度愈低。 The exchange sub-module 335 signals the mutation sub-module 334 to perform exchange operations on the mutation vector and generate a test vector. The exchange sub-module 335 exchanges each mutation vector with the corresponding target vector according to an exchange rule, and generates a new test vector. The exchange operation rule is shown in formula (11):

(11); where

Is the test vector;

Is the mutation vector;

Is the target vector;

It is the random value corresponding to each dimension, and its value is a random number between 0 and 1; CR is the exchange rate. If the exchange rate CR is larger, the similarity between the test vector and the mutation vector is higher; if the exchange rate CR is smaller, the similarity between the test vector and the mutation vector is lower.

(12)； 其中

為選擇後的目標向量；

為試驗向量；

為當前的目標向量；

為試驗向量的適應值差；

為當前的目標向量的適應值差。 The signal of the selection sub-module 336 is connected to the exchange sub-module 335, which compares the test vector and the best leader and selects the one that retains the largest adaptive threshold to become the surface polishing accuracy Y. Specifically, the selection sub-module 336 uses the adaptive threshold to evaluate whether the test vector can become the surface polishing accuracy Y , and its selection formula is shown in equation (12):

(12); where

Is the selected target vector;

Is the test vector;

Is the current target vector;

Is the fitness value difference of the test vector;

Is the fitness value difference of the current target vector.

(13)；

(14)； 其中

是ith粒子的速度；

是當前粒子的位置；

是粒子本身的最佳解；

是整個族群的最佳解；

為慣性權重；

為認知係數；

為社會係數；

及

為介於0到1之間的隨機亂數。 The processing parameter optimization module 340 calculates the best processing parameters corresponding to the surface grinding accuracy Y according to the optimization unit 350 for processing data optimization. The optimization unit 350 performs calculations on the complex processing parameters and surface polishing accuracy Y of each processing data to calculate these optimal processing parameters corresponding to the surface polishing accuracy Y. The calculation rules of the optimization unit 350 are shown in equations (13) and (14):

(13);

(14); where

Is the velocity of the ith particle;

Is the position of the current particle;

Is the best solution of the particle itself;

Is the best solution for the entire ethnic group;

Is the weight of inertia;

Is the cognitive coefficient;

Is the social coefficient;

and

It is a random random number between 0 and 1.

The grinding machine 10 grinds the workpiece according to the optimal processing parameters calculated by the processing parameter optimization module 340.

The processor 30 further includes an update data collection module 360, the update data collection module 360 signals the connection processing accuracy prediction module 310 and the processing parameter optimization module 340. The update data collection module 360 collects the surface grinding longitude and the best processing parameters to form an update data set. The machining accuracy prediction module 310 updates the grinding prediction model according to the update data set formed by the update data collection module 360 to generate an updated prediction model. In detail, with the long-term operation of the grinding machine 10, the wear of internal parts makes the surface grinding accuracy Y predicted by the grinding prediction model differ from the surface grinding accuracy Y obtained by the actual grinding of the grinding machine 10. By updating the forecast The model can make the surface polishing accuracy Y predicted by the intelligent ultrasonic-assisted polishing processing system 100 closer to the actual polishing accuracy.

Thereby, the intelligent ultrasonic-assisted grinding processing system 100 of the present invention predicts the surface grinding accuracy Y generated by the combination of different processing parameters through the grinding prediction model, and calculates the best processing parameters for obtaining the surface grinding accuracy Y. Effectively reduce the huge material and cost of the trial and error method, so that inexperienced operators can also set the corresponding optimal processing parameters according to the surface grinding accuracy Y to be achieved, and grind or polish the workpiece.

Please refer to Figures 1 to 5. Figure 4 is a schematic diagram showing the flow of the intelligent ultrasonic-assisted grinding and processing method 200 according to the second embodiment of the present invention; Figure 5 shows the intelligent ultrasonic in Figure 4 The schematic flow diagram of the dynamic grouping difference calculation rule S22 of the auxiliary grinding processing method 200. As shown in the figure, the intelligent ultrasonic-assisted grinding processing method 200 is used to predict the surface grinding accuracy Y of the workpiece after grinding. The intelligent ultrasonic-assisted grinding processing method 200 includes a processing data recording step S10, a processing accuracy prediction step S20, a processing parameter optimization step S30, an update data collection step S40, and a grinding step S50.

The processing data recording step S10 is to record the plural processing data of the grinding machine 10 in the database 20.

The processing accuracy prediction step S20 is based on the interval 2 fuzzy neural network model S21 to train these processing data and establish a grinding prediction model, where the interval 2 fuzzy neural network model S21 is adjusted by the dynamic clustering difference calculation rule S22 And produce the surface grinding precision Y. The processing accuracy prediction step S20 is executed by the processing accuracy prediction module 310. The interval 2 fuzzy neural network model S21 is executed by the interval 2 fuzzy neural network 320, and the dynamic grouping difference calculation rule S22 is executed by the dynamic grouping difference calculation unit 330.

The dynamic grouping difference calculation rule S22 includes an initialization sub-step S221, an adaptive threshold calculation sub-step S222, a grouping sub-step S223, a mutation sub-step S224, an exchange sub-step S225, and a selection sub-step S226.

The initialization sub-step S221 encodes the Gaussian mean value, Gaussian standard deviation, Gaussian displacement, and linear function weight into one body, where the interval-type 2 fuzzy neural network model S21 further includes plural individuals. The initialization sub-step S221 is performed through the initialization sub-module 331.

The adaptive threshold calculation sub-step S222 calculates the distance threshold and the adaptive threshold of each body, and defines the plural leaders of the plural groups. The adaptive threshold calculation sub-step S222 is executed through the adaptive threshold calculation sub-module 332.

The grouping sub-step S223 is to divide the individuals into these groups according to the distance threshold and adaptation threshold of each individual. The grouping sub-step S223 is performed by the grouping sub-module 333.

The mutation sub-step S224 generates a mutation vector from one of the leaders and the best leader of these leaders according to the Levi flight strategy. The mutation sub-step S224 is executed by the mutation sub-module 334.

The exchange sub-step S225 performs an exchange operation on the mutation vector and generates a test vector. The exchange sub-step S225 is performed through the exchange sub-module 335.

The selection sub-step S226 is to compare the test vector and the best leader and select the one that retains the largest adaptive threshold to become the surface polishing accuracy Y. The selection sub-step S226 is executed through the selection sub-module 336.

The processing parameter optimization step S30 is to optimize the processing data according to the optimization rules to calculate the plural optimal processing parameters corresponding to the surface grinding accuracy Y. The processing parameter optimization step S30 is executed through the processing parameter optimization module 340. The optimization rule calculates the multiple processing parameters of each processing data and the surface grinding accuracy Y to calculate the best processing parameters corresponding to the surface grinding accuracy Y.

The update data collection step S40 is to collect the surface grinding accuracy Y and these optimal processing parameters to form an update data group, and update the grinding prediction model according to the update data group to generate an update prediction model. The update data collection step S40 is performed through the update data collection module 360.

The grinding step S50 is to drive the grinding machine 10 to grind the workpiece according to these optimal processing parameters.

Thereby, the intelligent ultrasonic-assisted grinding processing method 200 of the present invention predicts the surface grinding accuracy Y generated by the combination of different processing parameters through the grinding prediction model, and calculates the best processing parameters for obtaining the surface grinding accuracy Y. Effectively reduce the huge material and cost of the trial and error method, so that inexperienced operators can also set the corresponding optimal processing parameters according to the surface grinding accuracy Y to be achieved, and grind or polish the workpiece.

Although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention. Anyone who is familiar with this technique can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection of the present invention The scope shall be subject to the definition of the attached patent application scope.

10: Grinding machine 20: Database 30: Processor 100: Intelligent ultrasonic-assisted grinding and processing system 200: Intelligent ultrasonic-assisted grinding and processing method 310: Machining accuracy prediction module 320: Interval type 2 fuzzy neural network 330: Dynamic clustering differential calculation unit 331: Initialization sub-module 332: Adaptive threshold calculation sub-module 333: Clustering sub-module 334: Mutation sub-module 335: Exchange sub-module 336: Selection sub-module 340: Processing parameters Optimization module 350: Optimization unit 360: Update data collection module S10: Processing data recording step S20: Processing accuracy prediction step S21: Interval type 2 fuzzy neural network model S22: Dynamic clustering difference calculation rule S221: Initialization sub-step S222 : Adaptive threshold calculation sub-step S223: clustering sub-step S224: mutation sub-step S225: exchange sub-step S226: selection sub-step S30: processing parameter optimization step S40: update data collection step S50: grinding step Layer1: first layer Layer2: The second layer Layer3: the third layer Layer4: the fourth layer Layer5: the fifth layer X ₁ , X _n : input value Y: surface polishing accuracy

Figure 1 is a block diagram of the intelligent ultrasonic-assisted grinding and processing system according to the first embodiment of the present invention; Figure 2 is a schematic diagram showing the interval-type fuzzy neural network of the intelligent ultrasonic-assisted grinding and processing system in Figure 1; Figure 3 is a block diagram of the dynamic grouping differential calculation unit of the intelligent ultrasonic-assisted grinding and processing system of Figure 1; Fig. 4 is a schematic flow chart of the intelligent ultrasonic-assisted grinding and processing method according to the second embodiment of the present invention; and Fig. 5 is a schematic flow chart of the dynamic grouping difference calculation rule of the intelligent ultrasonic-assisted grinding processing method in Fig. 4.

100: Intelligent ultrasonic assisted grinding and processing system

10: Grinding machine

20: Database

30: processor

310: Machining accuracy prediction module

320: Interval Type 2 Fuzzy Neural Network

330: Dynamic clustering difference calculation unit

340: Processing parameter optimization module

350: optimization unit

360: Update the data collection module

Claims (5)

An intelligent ultrasonic-assisted grinding and processing system for predicting the surface grinding accuracy of a workpiece after grinding. The intelligent ultrasonic-assisted grinding and processing system includes: A grinding machine; A database, the signal is connected to the grinding machine, and the plural processing data of the grinding machine are recorded; and A processor with signals connected to the grinding machine and the database, and the processor includes: A processing accuracy prediction module receives the processing data from the database, and the processing accuracy prediction module trains the processing data according to an interval 2 fuzzy neural network and establishes a grinding prediction model. The interval 2 The type fuzzy neural network is adjusted by a dynamic clustering difference calculation unit to produce the surface polishing accuracy; and A processing parameter optimization module, the signal is connected to the processing accuracy prediction module and receives the surface grinding accuracy, and the processing parameter optimization module calculates the optimal complex number corresponding to the surface grinding accuracy according to an optimization unit for the optimization of the processing data Processing parameters; Wherein, the grinding machine grinds the workpiece according to the optimal processing parameters. The intelligent ultrasonic-assisted grinding and processing system according to claim 1, wherein the interval type 2 fuzzy neural network includes: The first layer contains the processing data; A second layer, perform a fuzzification operation on the processed data, and calculate an interval two-type fuzzy set; A third layer, a cumulative multiplication operation is performed on the interval type-2 fuzzy set; A fourth layer, perform a reduction operation on the interval type 2 fuzzy set and a linear function weight, and calculate a type one fuzzy set; and A fifth layer, to perform a defuzzification operation on the one-type fuzzy set, and calculate the surface grinding accuracy; Among them, the interval type 2 fuzzy set includes a Gaussian mean value, a Gaussian standard deviation, and a Gaussian displacement. The intelligent ultrasonic-assisted grinding and processing system according to claim 2, wherein the dynamic grouping difference calculation unit includes: An initialization sub-module, encoding the Gaussian average value, the Gaussian standard deviation, the Gaussian displacement, and the linear function weight into a volume, wherein the interval type-2 fuzzy neural network further includes a plurality of the individuals; An adaptation threshold calculation sub-module, the signal is connected to the initialization sub-module, and a distance threshold and an adaptation threshold of each individual are calculated, and the plural leaders of plural groups are defined; A grouping sub-module, the signal is connected to the adaptive threshold calculation sub-module, and the individuals are divided into the groups according to the distance threshold and the adaptive threshold of each individual; A mutation sub-module, a signal is connected to the grouping sub-module, and a mutation vector is generated from one of the leaders and the best leader of one of the leaders according to a Levi flight strategy; An exchange sub-module, the signal is connected to the mutation sub-module, the mutation vector is subjected to an exchange operation and a test vector is generated; and A selection sub-module, a signal is connected to the exchange sub-module, and the test vector is compared with the best leader and the one with the largest adaptive threshold is selected to be retained as the surface polishing accuracy. The intelligent ultrasonic-assisted grinding and processing system according to claim 3, wherein the optimization unit calculates the plural processing parameters of each processing data and the surface grinding accuracy to calculate the optimal processing corresponding to the surface grinding accuracy parameter. The intelligent ultrasonic-assisted grinding and processing system according to claim 1, wherein the processor further includes: An update data collection module, signaled to connect the processing accuracy prediction module and the processing parameter optimization module, the update data collection module collects the surface grinding accuracy and the best processing parameters to form an update data set; Wherein, the machining accuracy prediction module updates the grinding prediction model according to the update data set formed by the update data collection module to generate an update prediction model.

Images