Parameter optimization method, device and computer-readable storage medium

Abstract

Disclosed in an embodiment of the present invention are a parameter optimization method, device, and computer-readable storage medium. The method comprises: establishing a one-to-one functional relationship between each parameter and each performance indicator based on a pre-established functional relationship between each performance indicator and all parameters; determining the current correlation coefficient between each parameter and each performance indicator based on the one-to-one functional relationship; obtaining the current weight of each performance indicator; obtaining the current influence coefficient of each parameter on the comprehensive performance and the important optimization parameters based on the current weight and the current correlation coefficient; obtaining the current correlation coefficient of each two parameters based on the current weight and the current correlation coefficient between each two parameters and each performance indicator; determining the adjustment parameter based on the degree of correlation with the important optimization parameter; and performing parameter optimization based on the important optimization parameter and the adjustment parameter. The technical solution in the embodiment of the present invention can improve the efficiency of parameter optimization.

Description

Technical Field

[0001] The present invention relates to the field of industrial technology, and in particular to a parameter optimization method, device and computer-readable storage medium. Background Art

[0002] Digital technology refers to the use of computers and networks to achieve digitization. It has been applied across various industries and fields, including traditional manufacturing plants. A digital factory utilizes computer hardware and software technologies to provide digital and information services to traditional manufacturing plants. A digital factory integrates various systems and databases related to the factory, product, and control systems. Through visualization, simulation, and big data, it improves the flexibility and efficiency of factory manufacturing processes.

[0003] CNC machining is an important part of modern digital factories, so it is necessary to have an efficient and intelligent CNC system.

[0004] CNC machine tools can process workpieces based on G-code. Currently, G-code can be automatically generated, but various parameters must be manually entered, which is not only inefficient but also cannot guarantee optimal parameters. Furthermore, changes in the external environment or processing requirements can also alter the optimal combination of CNC machine parameters. This necessitates manual parameter calculation and adjustment, a labor-intensive and inefficient process. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide, on the one hand, a parameter optimization method, and, on the other hand, provide a parameter optimization device and a computer-readable storage medium to improve the efficiency of parameter optimization.

[0006] A parameter optimization method proposed in an embodiment of the present invention includes: establishing a one-to-one functional relationship between each parameter and each performance indicator based on a pre-established functional relationship between each performance indicator and all parameters; for the current value of each parameter, determining the current correlation coefficient between the parameter and each performance indicator based on the one-to-one functional relationship; obtaining the current weight of each performance indicator; according to the current weight and the current correlation coefficient, obtaining the current influence coefficient of each parameter on the comprehensive performance, determining the parameter whose current influence coefficient reaches a set high threshold as an important optimization parameter, or determining the first one or more parameters with a higher current influence coefficient as an important optimization parameter; for every two parameters, obtaining the current correlation coefficient of every two parameters according to the current weight and the current correlation coefficient of each of the two parameters with each performance indicator; determining the parameter whose current correlation coefficient with the important optimization parameter reaches the set requirement as the adjustment parameter; and performing parameter optimization based on the important optimization parameter and the adjustment parameter.

[0007] In one embodiment, for the current value of each parameter, the current correlation coefficient between the parameter and each performance indicator is determined based on the functional relationship, including: for the current value of each parameter, the tangent slope of the curve corresponding to the one-to-one functional relationship between the parameter and each performance indicator at the current value is determined as the current correlation coefficient between the current value and the performance indicator.

[0008] In one embodiment, the method further includes: obtaining a correlation coefficient table between each parameter and each performance indicator according to the current correlation coefficient between each parameter and each performance indicator.

[0009] In one embodiment, the current influence coefficient of each parameter on the comprehensive performance is obtained based on the current weight and the current correlation coefficient, including: placing the current weight of each performance indicator into the correlation coefficient table to obtain a weighted correlation coefficient table, and adding the weighted current correlation coefficients corresponding to the same parameter in the weighted correlation coefficient table to obtain the current influence coefficient of each parameter on the comprehensive score.

[0010] In one embodiment, the method further includes: using different colors to represent different current correlation coefficient values in the correlation coefficient table to obtain a correlation cloud diagram between each parameter and each performance indicator.

[0011] In one embodiment, it further includes: establishing a knowledge graph of parameters based on the current correlation coefficient of every two parameters; the knowledge graph includes nodes representing each parameter and inter-node connections representing the correlation relationship between parameters; in the knowledge graph, the size of the node is proportional to the size of the influence coefficient of the parameter represented by the node, and the nodes corresponding to important optimization parameters and adjustment parameters are highlighted.

[0012] In one embodiment, it further includes: obtaining a current comprehensive score characterizing the current comprehensive performance of each performance indicator based on the current weight and the current value of each performance indicator; when the current comprehensive score meets the set requirements, determining the parameters corresponding to the current comprehensive score as the final optimization parameters; otherwise, executing the operation of determining the current correlation coefficient between the parameter and each performance indicator based on the one-to-one functional relationship for the current value of each parameter; the parameter optimization based on the important optimization parameters and the adjustment parameters includes: adjusting the values of each parameter according to the set rules or only adjusting the values of the important optimization parameters and the adjustment parameters in accordance with the principle of giving priority to adjusting the values of the important optimization parameters and the adjustment parameters, and returning to execute the operation of establishing a one-to-one functional relationship between each parameter and each performance indicator based on the pre-established functional relationship between each performance indicator and all parameters.

[0013] In one embodiment, it further includes: in response to a change in the current weight of each performance indicator, returning to execute the step of obtaining the current influence coefficient of each parameter on the comprehensive performance based on the current weight and the current correlation coefficient.

[0014] In one embodiment, the method further includes: in response to a user's change of an important optimization parameter or an adjustment parameter, performing parameter optimization based on the changed important optimization parameter or adjustment parameter.

[0015] The parameter optimization device provided in the embodiment of the present application includes: a first module for establishing a one-to-one functional relationship between each parameter and each performance indicator based on a pre-established functional relationship between each performance indicator and all parameters; a second module for determining, for the current value of each parameter, the current correlation coefficient between the parameter and each performance indicator based on the one-to-one functional relationship; a third module for obtaining the current weight of each performance indicator; a fourth module for obtaining the current influence coefficient of each parameter on the comprehensive performance based on the current weight and the current correlation coefficient, and determining the parameter whose current influence coefficient reaches a set high threshold as an important optimization parameter, or determining the first one or more parameters with a higher current influence coefficient as an important optimization parameter; a fifth module for obtaining the current correlation coefficient of each two parameters based on the current weight and the current correlation coefficient of each of the two parameters with each performance indicator, and determining the parameter whose current correlation coefficient with the important optimization parameter meets the set requirement as an adjustment parameter; and a sixth module for performing parameter optimization based on the important optimization parameter and the adjustment parameter.

[0016] In one embodiment, it further includes: a seventh module, which is used to obtain a correlation coefficient table between each parameter and each performance indicator based on the current correlation coefficient between each parameter and each performance indicator; different colors are used in the correlation coefficient table to represent different current correlation coefficient values to obtain a correlation cloud map between each parameter and each performance indicator.

[0017] In one embodiment, the fourth module places the current weight of each performance indicator into the correlation coefficient table to obtain a weighted correlation coefficient table, and adds the weighted current correlation coefficients corresponding to the same parameter in the weighted correlation coefficient table to obtain the current influence coefficient of each parameter on the comprehensive score.

[0018] In one embodiment, it further includes: an eighth module, which is used to establish a knowledge graph of parameters based on the current correlation coefficient of every two parameters; the knowledge graph includes nodes representing each parameter and inter-node connections representing the relationship between parameters; in the knowledge graph, the size of the node is proportional to the size of the influence coefficient of the parameter represented by the node, and the nodes corresponding to important optimization parameters and adjustment parameters are highlighted.

[0019] In one embodiment, it further includes: a ninth module, which is used to obtain a current comprehensive score characterizing the current comprehensive performance of each performance indicator based on the current weight and the current value of each performance indicator; a tenth module, which is used to determine the parameters corresponding to the current comprehensive score as the final optimization parameters when the current comprehensive score meets the set requirements; otherwise, instruct the second module to perform the corresponding operation; the sixth module adjusts the values of each parameter according to the set rules or only adjusts the values of the important optimization parameters and adjustment parameters according to the principle of giving priority to adjusting the values of the important optimization parameters and adjustment parameters, and instructs the first module to perform the corresponding operation.

[0020] Another parameter optimization device provided in an embodiment of the present application includes at least one memory and at least one processor, wherein: the at least one memory is used to store a computer program; the at least one processor is used to call the computer program stored in the at least one memory to execute the CNC parameter optimization method described in any of the above embodiments.

[0021] A computer-readable storage medium is provided in an embodiment of the present application, on which a computer program is stored; the computer program can be executed by a processor and implement the CNC parameter optimization method described in any of the above embodiments.

[0022] As can be seen from the above scheme, since each performance indicator can be assigned a weight in the embodiments of the present invention, all parameters can be optimized simultaneously based on the overall performance. Based on the coefficient of influence of each parameter on the overall performance, targeted optimization can be achieved, improving efficiency. Further adjustments can be made based on the degree of correlation between various parameters to compensate for possible degradation of other performance indicators, thereby improving parameter optimization efficiency.

[0023] In addition, the weight distribution can be changed at any time according to the external environment and processing requirements, and the parameter optimization direction can be adjusted.

[0024] In addition, the functional relationship between performance indicators and various parameters can be adjusted according to the characteristics of different machine tools. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, so that those skilled in the art will understand the above and other features and advantages of the present invention more clearly. In the accompanying drawings:

[0026] Figure 1 This is an exemplary flow chart of the parameter optimization method in an embodiment of the present invention.

[0027] Figure 2 This is a schematic diagram of a one-to-one functional relationship between performance indicators and parameters in an example of this application.

[0028] Figure 3 This is a schematic diagram of a correlation cloud diagram of parameters and performance indicators in an example of this application.

[0029] Figure 4 Schematic diagram of the current weights of performance indicators in an example of this application.

[0030] Figure 5 This is a diagram of the correlation coefficient between each two parameters in an example of this application.

[0031] Figure 6 A schematic diagram of the current influence coefficient of each parameter and the knowledge graph of the parameter in an example of this application.

[0032] Figure 7 This is a schematic diagram of the changes in parameters, performance indicators and comprehensive scores during the optimization process in an example of this application.

[0033] Figure 8 This is an exemplary structural diagram of the parameter optimization device in an embodiment of the present application.

[0034] Figure 9 This is an exemplary structural diagram of another parameter optimization device in an embodiment of the present application.

[0035] The accompanying drawings are numerals as follows:

[0036]

[0037] DETAILED DESCRIPTION

[0038] In the embodiment of the present invention, it is considered that the change of a certain parameter may lead to the change of more than one performance indicator, the correlation between different parameters is different, and the impact of different parameters on different performance indicators is also different. However, traditional parameter optimization technology can usually only optimize certain parameters, but cannot optimize all input parameters synchronously; and traditional parameter optimization technology usually only considers the improvement of a certain performance without considering the problem of other performance degradations that may be caused by the performance improvement, which makes the parameter optimization efficiency low and lacks coordination.

[0039] Therefore, the parameter optimization scheme proposed in the embodiments of the present invention establishes a mapping relationship library between parameters and performance indicators. Based on the functional relationship between each parameter and each performance indicator, the correlation coefficient between each parameter and each performance indicator is determined. A comprehensive evaluation score for the performance indicator is calculated based on the currently determined performance indicator value and the preset weights for each performance indicator. Important optimization parameters are determined based on the correlation coefficients and the preset weights for each performance indicator. Based on the correlation coefficients and weight distributions, the correlation coefficients between the parameters are calculated to establish a parameter knowledge graph. Based on the correlation coefficients, parameters closely related to important optimization parameters are set as adjustment parameters. Parameter optimization is performed based on the important optimization parameters and adjustment parameters.

[0040] In the specific implementation, the comprehensive score of the performance indicator can be calculated based on the currently determined performance indicator value and the predetermined weight of each performance indicator. When the comprehensive score meets the preset conditions, the parameter corresponding to the comprehensive score is the final optimization parameter; otherwise, according to the important optimization parameters and adjustment parameters, optimization is performed by adjusting the values of the important optimization parameters and adjustment parameters.

[0041] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is further described in detail with reference to the following examples.

[0042] Figure 1 FIG. 1 is an exemplary flow chart of a parameter optimization method according to an embodiment of the present invention. Figure 1 As shown, the method may include the following processes.

[0043] Step 101 : Based on the pre-established functional relationship between each performance indicator and all parameters, a one-to-one functional relationship is established between each parameter and each performance indicator.

[0044] In step 101, a functional relationship between each evaluation index y and all parameters x can be established, and the initial templates of all functions can be saved in a database. Developers can adjust the corresponding function coefficients according to the characteristics of different machine tools.

[0045] For example, the above functional relationship can be expressed by the following formula (1):

[0046]

[0047] Wherein, M is the predetermined coefficient matrix, M is the number of performance indicators, and n is the number of parameters.

[0048] According to the calculation formula y for each performance indicator i =f i (x1,x2,L,x n); i=1,2,···,m, through variable control, by giving the value of other parameters, determine the one-to-one functional relationship y between each performance indicator and each parameter i =f i (x j ); i = 1, 2, ···, m; j = 1, 2, ···, n. That is, for each current parameter, the values of all parameters except the current parameter are substituted into the pre-established functional relationship between each performance indicator and all parameters to obtain a one-to-one functional relationship between each parameter and each performance indicator.

[0049] Step 102: For the current value of each parameter, a current correlation coefficient between the parameter and each performance indicator may be determined based on the one-to-one functional relationship.

[0050] In step 102, for the current value of each parameter, the slope of the tangent line corresponding to the current value in the function graph of the one-to-one functional relationship between the parameter and each performance indicator is calculated. It can be defined as the current correlation coefficient between the parameter and the performance indicator For example, Figure 2 This is a schematic diagram of a one-to-one functional relationship between performance indicators and parameters in an example of this application.

[0051] In addition, after determining the current correlation coefficients between each parameter and each performance indicator, a correlation coefficient table between each parameter and each performance indicator can be established. In addition, in the correlation coefficient table, different colors can be used to represent different values of the current correlation coefficient, thereby obtaining a correlation cloud diagram between the parameters and the performance indicators. For example, Figure 3 This is a schematic diagram of a correlation cloud diagram of parameters and performance indicators in an example of this application. In this example, a correlation cloud diagram of parameters and performance indicators can be displayed to the user.

[0052] Step 103: Obtain the current weight of each performance indicator.

[0053] In one example, the current weight of each performance indicator may be preset and stored, and in step 103 , the stored current weight of each performance indicator may be obtained.

[0054] In another example, the user can assign different validity coefficients s to each performance indicator through the interface. i , in response to the received validity coefficient s i , normalize the effectiveness coefficients of all performance indicators to obtain the current weight of each performance indicator, as shown in the following formula (2):

[0055]

[0056] The weight distribution such as the effectiveness coefficient can be adjusted at any time according to changes in the external environment and processing requirements.

[0057] For example, Figure 4 Schematic diagram of the current weights of performance indicators in an example of this application. Figure 4 can be presented to the user, and the user can adjust the value of the validity coefficient, which can then be changed accordingly Figure 4 Medium-weighted pie chart.

[0058] Step 104: Based on the current weight and the current correlation coefficient, the current influence coefficient of each parameter on the comprehensive performance is obtained, and important optimization parameters can be determined based on the current influence coefficient. For example, the parameter whose current influence coefficient reaches a set upper threshold is determined as the important optimization parameter, or the first one or more parameters with the highest current influence coefficient are determined as the important optimization parameters.

[0059] In step 104, the current weight corresponding to each performance indicator can be brought into the correlation coefficient table to obtain a weighted correlation coefficient table, and then the weighted current correlation coefficients corresponding to the same parameter in the weighted correlation coefficient table are added together to obtain the current influence coefficient of each parameter on the comprehensive performance.

[0060] For example, according to Figure 3 The correlation cloud diagram of the parameters and performance indicators shown in the figure is used to bring the weights into the correlation coefficient table to obtain the weighted correlation coefficient table. By adding each row, the current influence coefficient h of each parameter on the comprehensive score shown in formula (4) can be obtained. i :

[0061]

[0062] Step 104 is performed whenever a weight distribution such as a validity coefficient is adjusted.

[0063] Important optimization parameters can be further filtered later. For example, if a parameter is not suitable for adjustment due to actual conditions, the user can filter the parameter through the interactive panel so that it is no longer optimized as an important optimization parameter.

[0064] Step 105: For every two parameters, the current correlation coefficient of each two parameters is obtained according to the current weight of each performance indicator and the current correlation coefficient between the two parameters and each performance indicator; the parameter whose current correlation coefficient with the important optimization parameter meets the set requirement (for example, greater than or equal to a threshold) is determined as the adjustment parameter, that is, the parameter closely related to the important optimization parameter is determined as the adjustment parameter.

[0065] Figure 5 Schematic diagram of the correlation coefficient between each two parameters in an example of this application. Figure 5As shown, the current correlation coefficient between parameters x1 and x2 It can be calculated according to the following formula (5):

[0066]

[0067] Furthermore, a parameter knowledge graph can be created, consisting of nodes representing each parameter and links between nodes that represent the relationships between parameters. The degree of association between each parameter is determined by the association coefficient. Furthermore, the size of each node in the knowledge graph can be proportional to the influence coefficient of the parameter it represents, and nodes corresponding to important optimization and adjustment parameters can be highlighted. Furthermore, the length of the links can be proportional to the value of the association coefficient.

[0068] For example, Figure 6 The current influence coefficient h of each parameter in this application example i Schematic diagram of the knowledge graph of and parameters. Figure 6 As shown, parameter x1 is an important optimization parameter, while parameters x2 and x3 are adjustment parameters, so parameters x1, x2 and x3 are in Figure 6 Highlighted in.

[0069] You can further filter adjustment parameters later. For example, if a parameter is not suitable for adjustment due to actual conditions, you can filter it through the interactive panel so that it is no longer optimized as an adjustment parameter.

[0070] Step 106: Parameter optimization is performed based on the important optimization parameters and the adjustment parameters.

[0071] In step 106, in one example, when the parameter is not the finalized parameter, the parameter value may be adjusted according to a predetermined rule based on the principle of first adjusting the values of the important optimization parameters and the adjustment parameters, and then the process returns to step 101. In another example, when the parameter is not the finalized parameter, only the values of the important optimization parameters and the adjustment parameters may be adjusted, and then the process returns to step 101.

[0072] In step 106, parameter optimization processing may be performed according to conventional parameter optimization techniques. Alternatively, the method may further include the following process.

[0073] In step 107, based on the current weights and current values of the performance indicators, a current comprehensive score representing the current comprehensive performance of each performance indicator may be calculated according to formula (3):

[0074] E=w1·y1+w2·y2+L+w m y m (3)

[0075] When determining the current value of each performance indicator, the current value of each performance indicator may be calculated based on a one-to-one functional relationship between each parameter and each performance indicator and the current value of each parameter.

[0076] Step 108 , determining whether the comprehensive score is greater than or equal to a set threshold. When the comprehensive score is greater than or equal to the set threshold, executing step 109 ; otherwise, executing step 102 .

[0077] In step 109 , the parameters corresponding to the comprehensive scores are determined as the final optimized parameters to be recommended to the user.

[0078] For example, Figure 7 Schematic diagram of the changes in parameters, performance indicators and comprehensive scores during the optimization process in an example of this application. Figure 7 As shown in Figure 2, during the optimization process, the influence coefficients and correlation coefficients of the parameters are reflected in the dynamic knowledge graph, allowing for the selection of new important optimization parameters and adjustment parameters. Furthermore, the current values of the parameters, the current values of the performance indicators, the current comprehensive score, and the adjustment trajectory of the parameters and performance indicators are all dynamically reflected.

[0079] In one example, a genetic algorithm can be used as a prototype for the optimization algorithm. A comprehensive score that considers the weights of performance indicators is used as the fitness function, and iterative calculations are performed. The mutation and crossover frequencies of important optimization parameters and adjustment parameters are significantly higher than those of other parameters.

[0080] During the optimization process, the values of various parameters are constantly changing, so the correlation coefficients of these parameters also change synchronously. Based on this, a dynamic knowledge graph of each parameter can be obtained. When important optimization parameters and adjustment parameters change, the iterative calculation is paused. The calculation resumes after new important optimization parameters and adjustment parameters are specified.

[0081] After readjusting the weight distribution of each performance indicator, the new comprehensive score is used as the fitness function, and the parameters before readjustment are used as the initial values of the new iterative calculation.

[0082] Figure 8 This is an exemplary structural diagram of the parameter optimization device in the embodiment of the present application. The device can be used to perform Figure 1 For details not disclosed in the device embodiment of this application, please refer to the corresponding description in the method embodiment of this application, which will not be repeated below. Figure 8 As shown, the device may include a first module 801, a second module 802, a third module 803, a fourth module 804, a fifth module 805, and a sixth module 806. In some examples, the device may also include one or more of a seventh module 807, an eighth module 808, a ninth module 809, and a tenth module 810.

[0083] The first module 801 is used to establish a one-to-one functional relationship between each parameter and each performance indicator based on the pre-established functional relationship between each performance indicator and all parameters.

[0084] The second module 802 is used to determine the current correlation coefficient between each parameter and each performance indicator based on the one-to-one functional relationship for the current value of each parameter.

[0085] The third module 803 is used to obtain the current weight of each performance indicator.

[0086] The fourth module 804 is used to obtain the current influence coefficient of each parameter on the comprehensive performance based on the current weight and the current correlation coefficient, and determine the parameters whose current influence coefficient reaches the set high threshold as important optimization parameters, or determine the first one or more parameters with higher current influence coefficients as important optimization parameters.

[0087] The fifth module 805 is used to obtain the current correlation coefficient of each two parameters based on the current weight and the current correlation coefficient of each of the two parameters with each performance indicator, and determine the parameter whose current correlation coefficient with the important optimization parameter meets the set requirements as the adjustment parameter.

[0088] The sixth module 806 is configured to perform parameter optimization based on the important optimization parameters and the adjustment parameters.

[0089] The seventh module 807 is used to obtain a correlation coefficient table between each parameter and each performance indicator based on the current correlation coefficient between each parameter and each performance indicator; different colors are used to represent different current correlation coefficient values in the correlation coefficient table to obtain a correlation cloud map between each parameter and each performance indicator.

[0090] In one example, the fourth module 804 places the current weight of each performance indicator into the correlation coefficient table to obtain a weighted correlation coefficient table, and adds the weighted current correlation coefficients corresponding to the same parameter in the weighted correlation coefficient table to obtain the current influence coefficient of each parameter on the comprehensive score.

[0091] The eighth module 808 is configured to establish a parameter knowledge graph based on the current correlation coefficient between each pair of parameters. The knowledge graph includes nodes representing each parameter and links between nodes representing the relationships between the parameters. In the knowledge graph, the size of a node is proportional to the influence coefficient of the parameter represented by the node, and nodes corresponding to important optimization parameters and adjustment parameters are highlighted.

[0092] The ninth module 809 is used to obtain a current comprehensive score representing the current comprehensive performance of each performance indicator based on the current weight and the current value of each performance indicator.

[0093] The tenth module 810 is used to determine the parameters corresponding to the current comprehensive score as the final optimized parameters when the current comprehensive score meets the set requirements; otherwise, instruct the second module to perform the corresponding operation.

[0094] The sixth module 806 adjusts the values of each parameter according to the set rules based on the principle of giving priority to the values of the important optimization parameters and adjustment parameters, or only adjusts the values of the important optimization parameters and adjustment parameters, and instructs the first module to perform corresponding operations.

[0095] In fact, the parameter optimization device provided in this embodiment of the present application can be implemented in various ways. For example, the parameter optimization device can be compiled into a plug-in installed in a smart terminal by using an application programming interface that complies with specific rules, or can be packaged into an application for users to download and use.

[0096] When compiled as a plug-in, the parameter optimization device can be implemented in a variety of plug-in forms, such as ocx, dll, and cab. The parameter optimization device provided by this implementation of the present application can also be implemented by using specific technologies, such as Flash plug-in technology, RealPlayer plug-in technology, MMS plug-in technology, MIDI plug-in technology, or ActiveX plug-in technology.

[0097] The parameter optimization method provided by this implementation of the present application can be stored in various storage media in the form of instruction storage or instruction set storage. These storage media include, but are not limited to, floppy disks, optical disks, DVDs, hard disks, flash memory, USB flash memory, CF cards, SD cards, MMC cards, SM cards, memory sticks, and xD cards.

[0098] In addition, the parameter optimization method provided by this embodiment of the present application can also be applied to flash memory (Nand-flash) based storage media, such as USB flash drives, CF cards, SD cards, SDHC cards, MMC cards, SM cards, memory sticks and xD cards.

[0099] It should be clear that the operating system operating in the computer can implement the functions of any of the above embodiments not only by executing the program code read by the computer from the storage medium, but also by using instructions based on the program code to implement part or all of the actual operations.

[0100] For example, Figure 9 This is an exemplary structural diagram of another parameter optimization device in the embodiment of the present application. The device can be used to perform Figure 1 The method shown, or for implementing Figure 8 The device in. Figure 9 As shown, the device may include at least one memory 91 and at least one processor 92. In addition, it may also include some other components, such as communication ports, input / output controllers, network communication interfaces, etc. These components communicate via a bus 93 or the like.

[0101] At least one memory 91 is used to store a computer program 911. In one example, a computer program may be understood to include Figure 8 In addition, at least one memory 91 can store an operating system, etc. Operating systems include but are not limited to: Android operating system, Symbian operating system, Windows operating system, Linux operating system, etc.

[0102] At least one processor 92 is configured to call a computer program stored in at least one memory 91 to execute the parameter optimization method described in the examples of this application. The processor 92 may be a CPU, a processing unit / module, an ASIC, a logic module, or a programmable gate array, and may receive and send data via a communication port.

[0103] The input / output controller has a display and input devices for inputting, outputting and displaying relevant data.

[0104] In the embodiments of the present application, a weight can be assigned to each performance indicator, and all parameters can be optimized simultaneously based on the overall performance. Based on the coefficient of influence of each parameter on the overall performance, targeted optimization can be achieved to improve efficiency. Further adjustments can be made based on the degree of correlation between various parameters to compensate for possible degradation of other performance indicators. This improves the efficiency of parameter optimization.

[0105] In addition, the weight distribution can be changed at any time according to the external environment and processing requirements, and the parameter optimization direction can be adjusted.

[0106] In addition, the functional relationship between performance indicators and various parameters can be adjusted according to the characteristics of different machine tools.

[0107] It should be understood that "and / or" as used herein is intended to include any and all possible combinations of one or more of the associated listed items.

[0108] The number of the embodiments of the present application is only used for description and does not represent the advantages of the embodiments.

[0109] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A parameter optimization method for CNC machine tool processing, characterized in that: include: Based on the pre-established functional relationship between each performance indicator and all parameters, a one-to-one functional relationship between each parameter and each performance indicator is established, wherein each parameter is a CNC machine tool parameter; For each parameter's current value, based on the one-to-one functional relationship, determine a current correlation coefficient between the parameter and each performance indicator; Get the current weight of each performance indicator; According to the current weight and the current correlation coefficient, the current influence coefficient of each parameter on the comprehensive performance is obtained, and the parameter whose current influence coefficient reaches a set high threshold is determined as an important optimization parameter, or the first one or more parameters with higher current influence coefficients are determined as important optimization parameters; For each two parameters, obtain a current correlation coefficient between the two parameters according to the current weight and the current correlation coefficient between the two parameters and each performance indicator; The parameter whose current correlation coefficient with the important optimization parameter meets the set requirement is determined as the adjustment parameter; Performing parameter optimization based on the important optimization parameters and the adjustment parameters; The current correlation coefficient between each parameter and each performance indicator is determined based on the functional relationship, including: For each current value of a parameter, determine the slope of a tangent line at the current value of a curve corresponding to a one-to-one functional relationship between the parameter and each performance indicator as a current correlation coefficient between the current value and the performance indicator; Further including: According to the current correlation coefficient between each parameter and each performance indicator, a correlation coefficient table between each parameter and each performance indicator is obtained; The current influence coefficient of each parameter on the comprehensive performance is obtained according to the current weight and the current correlation coefficient, including: The current weight of each performance indicator is placed in the correlation coefficient table to obtain a weighted correlation coefficient table, and the weighted current correlation coefficients corresponding to the same parameter in the weighted correlation coefficient table are added together to obtain the current influence coefficient of each parameter on the comprehensive score.

2. The method according to claim 1, characterized in that Further including: In the correlation coefficient table, different colors are used to represent different current correlation coefficient values, and a correlation cloud diagram of each parameter and each performance indicator is obtained.

3. The method according to claim 1, characterized in that Further including: Establishing a knowledge graph of the parameters based on the current correlation coefficient of each two parameters; the knowledge graph includes nodes representing each parameter and links between the nodes representing the correlation relationship between the parameters; In the knowledge graph, the size of a node is proportional to the size of the influence coefficient of the parameter represented by the node, and the nodes corresponding to important optimization parameters and adjustment parameters are highlighted.

4. The method according to any one of claims 1 to 3, characterized in that Further including: Performing a weighted summation on the current values of the performance indicators based on the current weights and the current values of the performance indicators to obtain a current comprehensive score representing the current comprehensive performance of the performance indicators; When the current comprehensive score meets the set requirements, the parameters corresponding to the current comprehensive score are determined as the final optimized parameters; Otherwise, performing the operation of determining the current correlation coefficient between the parameter and each performance indicator based on the one-to-one functional relationship for the current value of each parameter; The performing parameter optimization based on the important optimization parameters and the adjustment parameters includes: According to the principle of giving priority to adjusting the values of the important optimization parameters and adjustment parameters, the values of each parameter are adjusted according to the set rules or only the values of the important optimization parameters and adjustment parameters are adjusted, and the operation of establishing a one-to-one functional relationship between each parameter and each performance indicator based on the pre-established functional relationship between each performance indicator and all parameters is returned.

5. The method according to claim 4, characterized in that Further including: In response to the change of the current weight of each performance indicator, the step of obtaining the current influence coefficient of each parameter on the comprehensive performance according to the current weight and the current correlation coefficient is returned to be executed.

6. The method according to claim 4, characterized in that Further including: In response to a user's change of an important optimization parameter or an adjustment parameter, parameter optimization is performed based on the changed important optimization parameter or adjustment parameter.

7. Parameter optimization equipment for CNC machine tool processing, characterized in that, include: A first module is configured to establish a one-to-one functional relationship between each parameter and each performance indicator based on a pre-established functional relationship between each performance indicator and all parameters, wherein each parameter is a CNC machine tool parameter; A second module is configured to determine, for each parameter's current value, a current correlation coefficient between the parameter and each performance indicator based on the one-to-one functional relationship; The third module is used to obtain the current weight of each performance indicator; A fourth module is configured to obtain a current influence coefficient of each parameter on the comprehensive performance based on the current weight and the current correlation coefficient, and determine a parameter whose current influence coefficient reaches a set high threshold as an important optimization parameter, or determine one or more parameters with a higher current influence coefficient as the important optimization parameter; A fifth module is configured to obtain, for each two parameters, a current correlation coefficient between the two parameters and each performance indicator based on the current weights and the current correlation coefficients between the two parameters and each performance indicator, and determine as an adjustment parameter the parameter whose current correlation coefficient with the important optimization parameter meets the set requirements; A sixth module is configured to perform parameter optimization based on the important optimization parameters and the adjustment parameters; The second module determines, for the current value of each parameter, a current correlation coefficient between the parameter and each performance indicator based on the functional relationship, including: For each current value of a parameter, determine the slope of a tangent line at the current value of a curve corresponding to a one-to-one functional relationship between the parameter and each performance indicator as a current correlation coefficient between the current value and the performance indicator; The present invention also includes: a seventh module for obtaining a correlation coefficient table between each parameter and each performance indicator based on the current correlation coefficient between each parameter and each performance indicator; The fourth module puts the current weight of each performance indicator into the correlation coefficient table to obtain a weighted correlation coefficient table, and adds the weighted current correlation coefficients corresponding to the same parameter in the weighted correlation coefficient table to obtain the current influence coefficient of each parameter on the comprehensive score.

8. The device according to claim 7, characterized in that The seventh module further includes: In the correlation coefficient table, different colors are used to represent different current correlation coefficient values, and a correlation cloud diagram of each parameter and each performance indicator is obtained.

9. The device according to claim 7, characterized in that Further including: An eighth module is configured to establish a knowledge graph of the parameters based on the current correlation coefficient between each two parameters; the knowledge graph includes nodes representing each parameter and links between the nodes representing the relationship between the parameters; In the knowledge graph, the size of a node is proportional to the size of the influence coefficient of the parameter represented by the node, and the nodes corresponding to important optimization parameters and adjustment parameters are highlighted.

10. The device according to any one of claims 7 to 9, characterized in that Further including: A ninth module is configured to perform a weighted summation on the current values of the performance indicators based on the current weights and the current values of the performance indicators to obtain a current comprehensive score representing the current comprehensive performance of the performance indicators; a tenth module, configured to determine the parameters corresponding to the current comprehensive score as the final optimized parameters when the current comprehensive score meets the set requirements; otherwise, instruct the second module to perform the corresponding operation; The sixth module adjusts the values of each parameter according to the set rules based on the principle of giving priority to adjusting the values of the important optimization parameters and adjustment parameters, or only adjusts the values of the important optimization parameters and adjustment parameters, and instructs the first module to perform corresponding operations.

11. Parameter optimization device, characterized in that, comprising at least one memory and at least one processor, wherein: The at least one memory is used to store a computer program; The at least one processor is configured to call a computer program stored in the at least one memory to execute the parameter optimization method according to any one of claims 1 to 6.

12. A computer-readable storage medium having a computer program stored thereon; characterized in that: The computer program can be executed by a processor and implements the parameter optimization method according to any one of claims 1 to 6.

Images