Intelligent self-adaptive machining method capable of automatically identifying part to be machined
By collecting and analyzing spindle power data on a CNC machine tool, and adjusting the feed speed in combination with a fuzzy logic controller, automatic identification and adaptive processing of parts are achieved, solving the problem of not being able to automatically identify parts to be processed in the existing technology, and improving processing Efficiency and intelligence.
Patent Information
- Application Number
- CN202410972538.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-07-19
AI Technical Summary
The existing adaptive machining methods of CNC machine tools cannot automatically identify the parts to be processed, resulting in workers needing to pre-select the types of parts, which increases the workload and limits the application promotion of adaptive machining.
By installing power sensors on CNC machine tools, collecting spindle power data, and using segmented aggregation approximation algorithm and constrained derivative dynamic time bending algorithm to perform data dimensionality reduction and similarity matching, combined with a fuzzy logic controller to adjust the feed speed to realize parts Automatic identification and adaptive processing.
It realizes automatic identification of parts and adaptive adjustment of feed speed, improves processing efficiency and intelligence level, and reduces production time and cost.
Smart Images

Figure CN119017135A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of intelligent processing, and relates to an intelligent adaptive processing method capable of automatically identifying parts to be processed. Background Art
[0002] In the traditional CNC machining process, the cutting parameters are determined in the programming stage before machining, which is usually determined by computer-aided manufacturing software or the operator's experience. In fact, the use of fixed process parameters cannot adapt to the actual machining conditions, resulting in many unfavorable results: on the one hand, if the process parameters are set too small, it will lead to low machining efficiency and it will be difficult to give full play to the performance of CNC equipment; on the other hand, if the process parameters are set too large or the combination is unreasonable, the cutting force, cutting temperature, and cutting power will be too high, resulting in large tool deformation, fast wear rate, and reduced workpiece surface quality. In severe cases, it will also cause damage to the tool or even the spindle. CNC machine tool adaptive machining can adjust the cutting parameters in real time according to the machine tool machining load. It is an intelligent manufacturing technology that improves the intelligence of CNC machine tools, improves part machining efficiency, and reduces dependence on experienced operators.
[0003] Domestic scholars have conducted relevant research on adaptive machining of CNC machine tools. In the patent "Control method and device for CNC machine tools and their adaptive machining" (application number: CN202010930080.6), a deep learning model is used to predict the cutting force, and the optimal feed rate is autonomously found based on the predicted cutting force to achieve adaptive machining of CNC machine tools; in the patent "A machine tool adaptive control method based on GA-BP neural network algorithm" (application number: CN201910732917.3), the feed speed and spindle speed are optimized and adaptively adjusted in real time based on the neural network algorithm, which can effectively improve the machining efficiency and quality; in the paper "Online monitoring and machining parameters of composite material drilling surface roughness" In the paper "Study on Adaptive Optimization of Constant Power Constraint Machining Method with Fusion Chatter Control" (Journal of Mechanical Engineering, 2020, 56(02): 27-34+42.), an online monitoring model of hole wall roughness based on support vector regression was established, and the simulated annealing algorithm was used to optimize the drilling parameters under the current monitoring state to ensure the drilling quality; in the paper "Research on Adaptive Machining Method with Constant Power Constraint Fusion Chatter Control" (Mechanical Manufacturing and Automation, 2018, 47(05): 41-44+52.), based on fuzzy theory and variable speed cutting chatter suppression theory, the adjustment principles of machine tool machining parameters were formulated with machining efficiency as the goal, and constant power constrained adaptive machining with fusion chatter control was realized.
[0004] By analyzing the existing adaptive processing technology of CNC machine tools, it is found that the current adaptive processing method of CNC machine tools can improve processing efficiency by adjusting cutting parameters, but the existing adaptive processing method cannot automatically identify the parts to be processed. Before applying adaptive processing, the operator needs to pre-select the type of parts to be processed. When there are many types of processed parts, the workload of the workers is increased, making it difficult to promote adaptive processing technology in practical applications. Therefore, an intelligent adaptive processing method that can automatically identify the parts to be processed is needed. In view of the above problems, the present invention proposes an automatic identification method for parts to be processed, which can identify the type of parts to be processed according to the machine tool spindle power collected during the CNC processing process, and adjust the feed speed of the CNC machine tool in real time through the set constant reference power, thereby improving the processing efficiency of parts and enhancing the intelligent level of CNC processing. Summary of the invention
[0005] In order to solve the problem that the common CNC machine tool adaptive processing method requires manual selection of the type of parts to be processed, the present invention designs an intelligent adaptive processing method that can automatically identify the parts to be processed.
[0006] The technical solution of the present invention:
[0007] An intelligent adaptive machining method that can automatically identify the parts to be machined is as follows:
[0008] S1: Data collection and transmission: Collect the spindle power data when the CNC machine tool processes parts, and send the acquired spindle power data to the industrial computer;
[0009] S1.1: Install a power sensor at an appropriate position on the spindle controller of a CNC machine tool and use the power sensor to collect spindle power data during machining;
[0010] S1.2: Send the spindle power data to the industrial computer through the data transmission line;
[0011] S2: using an industrial computer to perform similarity matching and comparison between the spindle power data obtained in step S1 and the spindle power data in the database. If the similarity matching and comparison fails, step S3 is implemented; if the matching is successful, step S4 is implemented, and the database is stored in the industrial computer;
[0012] S2.1: Use the piecewise aggregation approximation algorithm (PAA algorithm) to perform dimension reduction processing on the spindle power data obtained in step S1 to obtain the spindle power data after dimension reduction;
[0013] S2.2: applying a constrained derivative dynamic time warping algorithm (CDDTW algorithm) to perform similarity matching and comparison between the reduced-dimensional spindle power data and each spindle power data in the database, and determining whether the optimal feed speed of the processed part exists in the database;
[0014] S2.2.1: Calculate the distance matrix D between the spindle power data after dimension reduction in step S2.1 and the first spindle power data in the database, and the element d in the i-th row and j-th column of the distance matrix D i,j The calculation formula is:
[0015]
[0016] Among them, d i,j is the element in the i-th row and j-th column of the distance matrix D; a i ′ is the numerical derivative of the i-th data point of the spindle power data after dimension reduction, and the calculation formula is: And a′1=a′2, a′ m =a′ m-1 ; b j ′ is the numerical derivative of the jth data point of the first spindle power data in the database, and the calculation formula is: And b1′=b2′, b′ n = b′ n-1 ; ω is the penalty intensity coefficient; m is the number of data points of the spindle power data after dimensionality reduction; n is the number of data points of the first spindle power data in the database;
[0017] S2.2.2: Solve the alignment path of the distance matrix D. The alignment path consists of path points in the distance matrix D that satisfy the following conditions: (1) The starting path point of the alignment path is d 1,1 , the end path point is d m,n ; (2) The next path point in the alignment path must be one of the three elements adjacent to the previous path point, and these three path points are located to the right, below, and below-right of the previous path point respectively; (3) The next path point is the one with the smallest value among the above three path points. If the values of the three path points are the same, the path point at the lower right is preferred, followed by the path point at the bottom, and finally the path point at the right;
[0018] S2.2.3: Calculate the alignment path smoothness S of the distance matrix D. The alignment path smoothness S formula is: Among them, N inc N is the total number of special path points in the alignment path, and the characteristic of these special path points is that they are located to the lower right of the previous path point; tot is the total number of all path points in the alignment path;
[0019] S2.2.4: Repeat steps S2.2.1 to S2.2.3 to calculate the alignment path smoothness S of the spindle power data after dimensionality reduction and each spindle power data in the database. If there is an alignment path smoothness S greater than the similarity threshold α, it is considered that the optimal feed speed of the processed part exists in the database, and the optimal feed speed corresponding to the spindle power data in the database with the largest alignment path smoothness S is selected as the optimal feed speed of the processed part; if there is no alignment path smoothness S greater than the similarity threshold α, it is considered that the optimal feed speed of the processed part is not in the database;
[0020] S2.2.5: If the optimal feed speed of the processed part is not in the database, a label is set for the reduced-dimensional spindle power data to obtain the reduced-dimensional spindle power data with the label;
[0021] Furthermore, in step S2.2.1, the penalty intensity coefficient ω is usually set to 0.6 to 0.8;
[0022] Furthermore, in step S2.2.4, the similarity threshold α is usually set to 60%.
[0023] S3: using the industrial computer to calculate the optimal feed speed of the processed part corresponding to the spindle power data obtained in S1, and saving the optimal feed speed and the spindle power data as the same data in the database;
[0024] S3.1: Set a constant power reference value Pi for the spindle power data with label after dimension reduction in step S2.2.5 ref , select the dual-input single-output fuzzy logic controller as the solution model of the feed rate adaptive control model, which is used to solve the feed rate optimization value. The input of the fuzzy logic controller is the power deviation e and the power deviation change rate ec. The power deviation e formula is: e=P o -Pi ref , where P o is the spindle power data after dimensionality reduction with labels; the power deviation change rate ec formula is: Where de is the differential of power deviation, and dt is the differential of time;
[0025] S3.2: Use negative large NB, negative medium NM, negative small NS, zero ZO, positive small PS, positive medium PM and positive large PB language variables to describe the power deviation e, power deviation change rate ec and optimal feed speed f c , e, ec and f c The fuzzy domain is set to [-p, p], and its fuzzy sets are represented by {NB, NM, NS, ZO, PS, PM, PB}, using triangular functions as e, ec, and f c The membership function of
[0026] S3.3: Formulate a fuzzy control rule table, use the Mamdani fuzzy reasoning method to calculate the fuzzy membership output, use the area centroid method to perform defuzzification calculation, and obtain the optimal feed speed f c ;
[0027] S3.4: saving the obtained optimal feed speed and the dimension-reduced spindle power data with labels as the same piece of data into the database;
[0028] Furthermore, in step S3.2, e, ec and f c The p in the fuzzy domain [-p, p] is a positive integer not greater than 7.
[0029] S4: Adaptively control the feed rate of the machine tool by using the industrial computer: select the best feed speed consistent with the part to be processed from the database on the industrial computer, use the best feed speed to solve the feed rate control value, and send the feed rate control value to the numerical control system of the numerical control machine tool, so as to realize adaptive processing of the numerical control machine tool;
[0030] S4.1: Set the feed rate control value of the CNC machine tool to M f , the calculation formula is Among them, f c is the optimal feed speed stored in the database, f o The feed rate set for the machining program;
[0031] S4.2: The industrial computer and the CNC system of the CNC machine tool are connected via a network cable for real-time communication;
[0032] S4.3: Set the feed rate control value M f The data is sent to the CNC system, and the machine tool’s built-in PLC module is used to realize adaptive control of the machine tool’s feed rate.
[0033] Beneficial effects of the present invention:
[0034] (1) The intelligent adaptive processing method of the present invention can automatically identify the type of parts to be processed, and select corresponding control parameters for adaptive processing, thereby improving the intelligent level of adaptive processing of CNC machine tools.
[0035] (2) The intelligent adaptive processing method of the present invention can automatically identify the parts to be processed, thereby improving the processing efficiency of the parts and saving production time and cost.
[0036] (3) The intelligent adaptive processing method of the present invention can automatically identify the parts to be processed and can adaptively adjust the feed rate during the processing of the CNC machine tool, thereby improving the intelligence level of the CNC machine tool. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 is a schematic diagram of the arrangement of the power sensor of the embodiment;
[0038] Figure 2 This is a diagram showing the effect of the adaptive control of the feed rate in Example 1;
[0039] Figure 3 This is the effect diagram of the adaptive control of the feed rate of Example 2;
[0040] Figure 4 Flow chart of the method of the present invention.
[0041] In the figure: 1 is a three-axis vertical machining center; 2 is the spindle servo motor; 3 is the workbench; 4 is the power sensor; 5 is the spindle. DETAILED DESCRIPTION
[0042] The specific implementation of the present invention is further described below in conjunction with the accompanying drawings and technical solutions.
[0043] The CNC machine tool used in this embodiment is a three-axis vertical machining center, and the control methods of other CNC machine tools refer to this embodiment.
[0044] Example 1
[0045] The intelligent adaptive machining method that can automatically identify the parts to be machined is achieved through the following steps:
[0046] S1: Data collection and transmission, specifically, collecting spindle power data when the CNC machine tool processes part A, and sending the acquired spindle power data to the industrial computer;
[0047] The S1 is specifically divided into two steps:
[0048] S1.1: If Figure 1 As shown, a power sensor 4 is installed at an appropriate position of the three-axis vertical machining center. The spindle 5 of the three-axis vertical machining center 1 of this embodiment is located above the workbench 3, and a spindle servo motor 2 is connected above the spindle 5. The power sensor 4 is arranged on the spindle servo motor 2, and its three current induction coils are respectively sleeved on the three power lines U, V, and W of the spindle motor, and the voltage is connected to the three power lines U, V, and W in parallel;
[0049] S1.2: Send the spindle power data to the industrial computer via the data transmission line.
[0050] S2: using an industrial computer to perform similarity matching and comparison between the spindle power data obtained in step S1 and the spindle power data in the database;
[0051] The S2 is specifically divided into two steps:
[0052] S2.1: Use the piecewise aggregation approximation algorithm (PAA algorithm) to perform dimension reduction processing on the spindle power data obtained in step S1 to obtain the spindle power data after dimension reduction;
[0053] S2.2: applying a constrained derivative dynamic time warping algorithm (CDDTW algorithm) to perform similarity matching and comparison between the reduced-dimensional spindle power data and each spindle power data in the database, and determining whether the optimal feed speed of the processed part exists in the database;
[0054] Specifically:
[0055] S2.2.1: Apply formula (1) to calculate the distance matrix D between the spindle power data after dimension reduction in step S2.1 and the first spindle power data in the database, where the value of ω in formula (1) is 0.8;
[0056] S2.2.2: Solve the alignment path of the distance matrix D. The alignment path consists of path points in the distance matrix D that satisfy the following conditions: (1) The starting path point of the alignment path is d 1,1 , the end path point is d m,n ; (2) The next path point in the alignment path must be one of the three elements adjacent to the previous path point, and these three path points are located to the right, below, and below-right of the previous path point respectively; (3) The next path point is the one with the smallest value among the above three path points. If the values of the three path points are the same, the path point at the lower right is preferred, followed by the path point at the bottom, and finally the path point at the right;
[0057] S2.2.3: Calculate the alignment path smoothness S of the distance matrix D. The alignment path smoothness S formula is: Among them, N inc N is the total number of special path points in the alignment path, and the characteristic of these special path points is that they are located to the lower right of the previous path point; tot is the total number of all path points in the alignment path;
[0058] S2.2.4: Repeat steps S2.2.1 to S2.2.3 to calculate the alignment path smoothness S of the reduced-dimensional spindle power data and each spindle power data in the database. The calculation results are shown in Table 1:
[0059] Table 1A Part and the alignment path smoothness S of each spindle power data in the database
[0060]
[0061] In this example, the similarity threshold α is 60%, and the alignment path smoothness S in Table 1 is less than 60%, so it is considered that the optimal feed speed of the processed part A is not in the database;
[0062] S2.2.5: setting a label for the spindle power data after dimension reduction as the spindle power data of the third part, thereby obtaining the spindle power data after dimension reduction whose label is the spindle power data of the third part;
[0063] S3: using the industrial computer to calculate the optimal feed speed of the processed part corresponding to the spindle power data of the third part in step S2.2.5, and saving the optimal feed speed and the spindle power data of the third part as the same data in the database;
[0064] The S3 is specifically divided into four steps:
[0065] S3.1: Set a constant power reference value Pi for the spindle power data with label after dimension reduction in step S2.2.5 ref , select the dual-input single-output fuzzy logic controller as the solution model of the feed rate adaptive control model, which is used to solve the feed rate optimization value. The input of the fuzzy logic controller is the power deviation e and the power deviation change rate ec. The power deviation e formula is: e=P o -Pi ref , where P o is the spindle power data after dimensionality reduction with labels; the power deviation change rate ec formula is: Where de is the differential of power deviation, and dt is the differential of time;
[0066] S3.2: Use negative large NB, negative medium NM, negative small NS, zero ZO, positive small PS, positive medium PM and positive large PB language variables to describe the power deviation e, power deviation change rate ec and optimal feed speed f c , e, ec and f c The fuzzy domain is set to [-6, 6], and its fuzzy sets are represented by {NB, NM, NS, ZO, PS, PM, PB}, using triangular functions as e, ec, and f c The membership function of
[0067] S3.3: Based on expert experience, a fuzzy control rule table is formulated, as shown in Table 2. The traditional fuzzy reasoning method (Mamdani fuzzy reasoning method) is used to calculate the fuzzy membership output, and the area centroid method is used for defuzzification calculation to obtain the optimal feed speed f c ;
[0068] Table 2 Rule diagram of fuzzy control module
[0069]
[0070] S3.4: saving the obtained optimal feed speed and the dimension-reduced spindle power data with labels as the same piece of data into the database;
[0071] S4: Adaptively control the feed rate of the machine tool by using the industrial computer: select the optimal feed speed saved in step S3.4 in the database on the industrial computer, use the optimal feed speed to solve the feed rate control value, and send the feed rate control value to the numerical control system of the numerical control machine tool, thereby realizing adaptive processing of the numerical control machine tool;
[0072] The S4 is specifically divided into three steps:
[0073] S4.1: Set the feed rate control value of the CNC machine tool to M f , the calculation formula is Among them, f c is the optimal feed speed stored in the database, f o The feed rate set for the machining program;
[0074] S4.2: The industrial computer and the CNC system of the CNC machine tool are connected via a network cable for real-time communication;
[0075] S4.3: Set the feed rate control value M f The data is sent to the numerical control system, and the machine tool feed rate is adaptively controlled through the built-in PLC module of the machine tool. The adaptive control effect of the feed rate in this embodiment is as follows: Figure 2 shown.
[0076] The technical effect of this embodiment is: the spindle power data of part A is compared with the data in the database. If the match fails, the power data of part A and the corresponding optimal feed speed are saved in the database as the spindle power data of the third part. The optimal feed speed corresponding to the spindle power data of the third part is used to adaptively control the feed rate of the machine tool, which improves the part processing efficiency by 15.4% and saves production time costs.
[0077] Example 2
[0078] The intelligent adaptive machining method that can automatically identify the parts to be machined is achieved through the following steps:
[0079] S1: data collection and transmission, specifically, collecting the spindle power data when the CNC machine tool processes the part B, and sending the acquired spindle power data to the industrial computer; S1 is specifically divided into two steps, which are the same as S1 in Example 1;
[0080] S2: Use an industrial computer to perform similarity matching and comparison between the spindle power data obtained in step S1 and the spindle power data in the database; S2 is specifically divided into two steps: steps S2.1, S2.2.1, S2.2.2, S2.2.3 and S2.2.4 are the same as the corresponding steps in Example 1; the calculation results of the alignment path smoothness S are shown in Table 3:
[0081] Table 3B Parts and each spindle power data in the database Alignment path smoothness S
[0082]
[0083] In this example, the similarity threshold α is 60%, and the alignment path smoothness of the spindle power data of part B after dimension reduction in Table 3 and the spindle power data of the third part in the database is greater than 60%. It is considered that the optimal feed speed of the processed part B is the same as the optimal feed speed corresponding to the spindle power data of the third part, and step S4 is directly implemented;
[0084] S4: Adaptive control of the feed rate of the machine tool by using the industrial computer: Select the optimal feed rate corresponding to the spindle power data of the third part in the database on the industrial computer, use the optimal feed rate corresponding to the spindle power data of the third part to solve the feed rate control value, and send the feed rate control value to the CNC system of the CNC machine tool, so as to achieve adaptive processing of the CNC machine tool; S4 is specifically divided into three steps, which are the same as S4 of Example 1. The adaptive control effect of the feed rate of this embodiment is as follows: Figure 3 shown.
[0085] The flow chart of the method of the present invention is as follows Figure 4 shown.
[0086] The technical effect of this embodiment is: the spindle power data of part B is compared with the data in the database. After a successful match, the optimal feed speed corresponding to the spindle power data of the third part is used to adaptively control the feed rate of the machine tool, thereby improving the part processing efficiency by 14.9% and saving production time costs.
[0087] It should be noted that the above specific embodiments of the present invention are only used to exemplify the principles and processes of the present invention and do not constitute a limitation of the present invention. Therefore, any modifications and equivalent substitutions made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention.
Claims
1. An intelligent adaptive processing method capable of automatically identifying parts to be processed, characterized in that: Here are the steps: S1. Data collection and transmission: Collect the spindle power data when the CNC machine tool processes parts, and send the acquired spindle power data to the industrial computer; S2: using an industrial computer to perform similarity matching and comparison between the spindle power data obtained in step S1 and the spindle power data in the database. If the similarity matching and comparison fails, step S3 is implemented; if the matching is successful, step S4 is implemented, and the database is stored in the industrial computer; S3: using the industrial computer to calculate the optimal feed speed of the processed part corresponding to the spindle power data obtained in step S1, and saving the optimal feed speed and the spindle power data as the same piece of data in the database; S4: Adaptively control the feed rate of the machine tool using an industrial computer: select the optimal feed speed consistent with the part to be processed from the database on the industrial computer, use the optimal feed speed to solve the feed rate control value, and send the feed rate control value to the CNC system of the CNC machine tool, thereby realizing adaptive processing of the CNC machine tool.
2. The intelligent adaptive processing method capable of automatically identifying the parts to be processed according to claim 1, characterized in that: The specific steps of step S1 are as follows: S1: Data collection and transmission: Collect the spindle power data when the CNC machine tool processes parts, and send the acquired spindle power data to the industrial computer; S1.1: Install a power sensor at an appropriate position on the spindle controller of a CNC machine tool and use the power sensor to collect spindle power data during machining; S1.2: Send the spindle power data to the industrial computer through the data transmission line.
3. The intelligent adaptive processing method capable of automatically identifying the parts to be processed according to claim 1, characterized in that: The specific steps of step S2 are as follows: S2.1: Use a segmented aggregation approximation algorithm to perform dimensionality reduction processing on the spindle power data obtained in step S1 to obtain the spindle power data after dimensionality reduction; S2.2: applying a constrained derivative dynamic time warping algorithm to perform similarity matching and comparison between the reduced-dimensional spindle power data and each spindle power data in the database, and determining whether the optimal feed speed of the machined part exists in the database; S2.2.1: Calculate the distance matrix D between the spindle power data after dimension reduction in step S2.1 and the first spindle power data in the database, and the element d in the i-th row and j-th column of the distance matrix D i,j The calculation formula is: Among them, d i,j is the element in the i-th row and j-th column of the distance matrix D; a i ′ is the numerical derivative of the i-th data point of the spindle power data after dimension reduction, and the calculation formula is: And a′1=a′2, a′ m =a′ m-1 ; b j ′ is the numerical derivative of the jth data point of the first spindle power data in the database, and the calculation formula is: And b1′=b2′, b′ n = b′ n-1 ; ω is the penalty intensity coefficient; m is the number of data points of the spindle power data after dimensionality reduction; n is the number of data points of the first spindle power data in the database; S2.2.2: Solve the alignment path of the distance matrix D. The alignment path consists of path points in the distance matrix D that satisfy the following conditions: (1) The starting path point of the alignment path is d 1,1 , the end path point is d m,n ; (2) The next path point in the alignment path must be one of the three elements adjacent to the previous path point, and these three path points are located to the right, below, and below-right of the previous path point respectively; (3) The next path point is the one with the smallest value among the above three path points. If the values of the three path points are the same, the path point at the lower right is preferred, followed by the path point at the bottom, and finally the path point at the right; S2.2.3: Calculate the alignment path smoothness S of the distance matrix D. The alignment path smoothness S formula is: Among them, N inc N is the total number of special path points in the alignment path, and the characteristic of these special path points is that they are located to the lower right of the previous path point; tot is the total number of all path points in the alignment path; S2.2.4: Repeat steps S2.2.1 to S2.2.3 to calculate the alignment path smoothness S of the spindle power data after dimensionality reduction and each spindle power data in the database. If there is an alignment path smoothness S greater than the similarity threshold α, it is considered that the optimal feed speed of the processed part exists in the database, and the optimal feed speed corresponding to the spindle power data in the database with the largest alignment path smoothness S is selected as the optimal feed speed of the processed part; if there is no alignment path smoothness S greater than the similarity threshold α, it is considered that the optimal feed speed of the processed part is not in the database; S2.2.5: If the optimal feed speed of the processed part is not in the database, a label is set for the reduced-dimensional spindle power data to obtain the reduced-dimensional spindle power data with the label.
4. The intelligent adaptive processing method capable of automatically identifying the parts to be processed according to claim 3 is characterized in that: In step S2.2.1, the penalty intensity coefficient ω is usually set to 0.6 to 0.
8.
5. The intelligent adaptive processing method capable of automatically identifying the parts to be processed according to claim 3 is characterized in that: In step S2.2.4, the similarity threshold α is usually set to 60%.
6. The intelligent adaptive processing method capable of automatically identifying the parts to be processed according to claim 3 is characterized in that: The specific steps of step S3 are as follows: S3.1: Set a constant power reference value Pi for the spindle power data with label after dimension reduction in step S2.2.5 ref , select the dual-input single-output fuzzy logic controller as the solution model of the feed rate adaptive control model, which is used to solve the feed rate optimization value. The input of the fuzzy logic controller is the power deviation e and the power deviation change rate ec. The power deviation e formula is: e=P o -Pi ref , where P o is the spindle power data after dimensionality reduction with labels; the power deviation change rate ec formula is: Where de is the differential of power deviation, and dt is the differential of time; S3.2: Use negative large NB, negative medium NM, negative small NS, zero ZO, positive small PS, positive medium PM and positive large PB language variables to describe the power deviation e, power deviation change rate ec and optimal feed speed f c , e, ec and f c The fuzzy domain is set to [-p, p], and its fuzzy sets are represented by {NB, NM, NS, ZO, PS, PM, PB}, using triangular functions as e, ec, and f c The membership function of S3.3: Formulate a fuzzy control rule table, use the Mamdani fuzzy reasoning method to calculate the fuzzy membership output, use the area centroid method to perform defuzzification calculation, and obtain the optimal feed speed f c ; S3.4: The obtained optimal feed speed and the dimension-reduced spindle power data with labels are saved as the same piece of data in the database.
7. The intelligent adaptive processing method capable of automatically identifying the parts to be processed according to claim 6, characterized in that: In step S3.2, e, ec and f c The p in the fuzzy domain [-p, p] is a positive integer not greater than 7.
8. The intelligent adaptive processing method capable of automatically identifying the parts to be processed according to claim 1, characterized in that: The specific steps of step S4 are as follows: S4.1: Set the feed rate control value of the CNC machine tool to M f , the calculation formula is Among them, f c is the optimal feed speed stored in the database, f o The feed rate set for the machining program; S4.2: The industrial computer and the CNC system of the CNC machine tool are connected via a network cable for real-time communication; S4.3: Set the feed rate control value M f The data is sent to the CNC system, and the machine tool’s built-in PLC module is used to realize adaptive control of the machine tool’s feed rate.
Citation Information
Patent Citations
Numerically-controlled machine tool and and control method and device for self-adaptive machining of numerically-controlled machine tool
CN112180833A
Adaptive machine tool control method based on GA-BP neural network algorithm
CN110488754A
Daily load curve clustering method based on PLR-DTW
CN112149052A
Numerical control cutter state on-line monitoring system
CN115716218A
Machine tool process parameter adaptive control method based on multi-neural network fusion
CN117250912A
Cited By
High-efficiency automatic control platform for multi-axis machining of parts
CN119960389A
