Parameter range determination method and device, numerical control system and storage medium

Abstract

The invention discloses a parameter range determination method and device, a numerical control system, a storage medium and a computer program product. Parameters are parameters input into the numerical control system. The method comprises the steps that after the numerical control system is started, real-time operation data of the numerical control system and the preset input range of parameters are substituted into a genetic algorithm model, the target input range of the parameters is determined, and the input range of the parameters in the numerical control system is set as the target input range. According to the scheme, the parameter range of the numerical control system is optimized through the genetic algorithm, the reasonability and adaptability of parameter setting are ensured, the machining precision is improved, the production efficiency is improved, and equipment abrasion is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of numerical control systems, and specifically relates to a method and device for determining a parameter range, a numerical control system, a storage medium and a computer program product. Background Art

[0002] In modern manufacturing, CNC systems are the core technology for achieving automated processing and product quality control. CNC systems control the movement and processing of machine tools through programs, and the range setting of system input parameters is crucial to ensure processing accuracy, improve production efficiency and equipment safety. The parameter range is usually set in advance and adjusted based on limited empirical data. This method is prone to errors and is difficult to achieve complex precision control and optimize the processing process, especially when faced with the diversity of workpieces, changes in material properties and aging equipment. Improper parameter range setting usually leads to problems such as reduced processing accuracy, increased equipment wear, and reduced production efficiency.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The purpose of the present invention is to provide a method, device, numerical control system, storage medium and computer program product for determining a parameter range, so as to solve the problem that improper parameter range setting in the numerical control system in related schemes leads to decreased machining accuracy, increased equipment wear and low production efficiency, so as to achieve the effect of optimizing the parameter range of the numerical control system by using a genetic algorithm, ensuring the rationality and adaptability of the parameter setting, improving machining accuracy, increasing production efficiency and reducing equipment wear.

[0005] The present invention provides a method for determining a parameter range, wherein the parameter is a parameter input into a numerical control system; the method comprises: after the numerical control system is started, obtaining real-time operation data of the numerical control system and a preset input range of the parameter; bringing the real-time operation data and the preset input range of the parameter into a preset genetic algorithm model to obtain a target input range of the parameter; and setting the input range of the parameter in the numerical control system to the target input range.

[0006] In some embodiments, the real-time operation data and the preset input range of the parameter are brought into a preset genetic algorithm model to obtain the target input range of the parameter, including: using the real-time operation data to encode the parameters in the preset genetic algorithm model, and using the real-time operation data to define the fitness function of the preset genetic algorithm model; generating an initial population according to the preset input range of the parameter; performing genetic operations using the fitness function and the initial population to obtain a final population; and performing fitness evaluation on the final population to obtain the target input range of the parameter.

[0007] In some embodiments, the fitness function and the initial population are used to perform genetic operations to obtain a final population, including: using the fitness function to evaluate the fitness value of each individual in the initial population; selecting a parent individual from the initial population according to a preset selection strategy and the fitness value of each individual in the initial population; performing a crossover operation on the parent individual using a preset crossover probability to obtain a child population; the child population includes at least one new individual; performing a mutation operation on the new individual in the child population using a preset mutation probability; and determining the child population after the mutation operation as the final population.

[0008] In some embodiments, it also includes: performing an iterative operation until the number of iterations is equal to a preset maximum number of iterations; the iterative operation is to determine the final population as a new initial population, and iteratively perform genetic operations using the fitness function and the new initial population to obtain the final population.

[0009] In some embodiments, performing fitness evaluation on the final population to obtain the target input range of the parameter includes: using the fitness function to evaluate the fitness value of each individual in the final population; and taking the individual with the highest fitness value in the final population as the target input range of the parameter.

[0010] In some embodiments, it also includes: when inputting the parameter into the input numerical control system, determining whether the input parameter is within the target input range; if the input parameter is not within the target input range, issuing a prompt message that the parameter is out of the set range.

[0011] Matching the above method, the present invention provides, on the other hand, a device for determining a parameter range, wherein the parameter is a parameter input into a numerical control system; the device comprises: an acquisition unit, configured to acquire real-time operation data of the numerical control system and a preset input range of the parameter after the numerical control system is started; an optimization unit, configured to bring the real-time operation data and the preset input range of the parameter into a preset genetic algorithm model to obtain a target input range of the parameter; the optimization unit is further configured to set the input range of the parameter in the numerical control system to the target input range.

[0012] In some embodiments, the optimization unit brings the real-time operation data and the preset input range of the parameter into a preset genetic algorithm model to obtain the target input range of the parameter, including: encoding the parameters in the preset genetic algorithm model using the real-time operation data, and defining the fitness function of the preset genetic algorithm model using the real-time operation data; generating an initial population according to the preset input range of the parameter; performing genetic operations using the fitness function and the initial population to obtain a final population; and performing fitness evaluation on the final population to obtain the target input range of the parameter.

[0013] In some embodiments, the optimization unit uses the fitness function and the initial population to perform genetic operations to obtain a final population, including: using the fitness function to evaluate the fitness value of each individual in the initial population; selecting a parent individual from the initial population according to a preset selection strategy and the fitness value of each individual in the initial population; performing a crossover operation on the parent individual using a preset crossover probability to obtain a child population; the child population includes at least one new individual; performing a mutation operation on the new individual in the child population using a preset mutation probability; and determining the child population after the mutation operation as the final population.

[0014] In some embodiments, the optimization unit is further configured to perform an iterative operation until the number of iterations is equal to a preset maximum number of iterations; the iterative operation is to determine the final population as a new initial population, and iteratively perform genetic operations using the fitness function and the new initial population to obtain the final population.

[0015] In some embodiments, the optimization unit performs fitness evaluation on the final population to obtain the target input range of the parameter, including: using the fitness function to evaluate the fitness value of each individual in the final population; and taking the individual with the highest fitness value in the final population as the target input range of the parameter.

[0016] In some embodiments, the optimization unit is further configured to determine whether the input parameter is within the target input range when the parameter is input into the input numerical control system; if the input parameter is not within the target input range, a prompt message is issued indicating that the parameter exceeds the set range.

[0017] Matching the above-mentioned device, the present invention further provides a numerical control system on the other hand, including: the device for determining the parameter range mentioned above.

[0018] In accordance with the above method, the present invention provides a storage medium on another aspect, wherein the storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the method for determining the parameter range described above.

[0019] In accordance with the above method, the present invention provides a computer program product on another aspect, wherein the computer program product includes a computer program, and when the computer program product is processed and executed, the steps of the method for determining the parameter range are implemented.

[0020] The solution of the present invention, after the CNC system is started, brings the real-time operation data of the CNC system and the preset input range of the parameters into the genetic algorithm model to determine the target input range of the parameters. Thus, by using the genetic algorithm to optimize the parameter range of the CNC system, the rationality and adaptability of the parameter setting are ensured, the processing accuracy is improved, the production efficiency is increased, and the equipment wear is reduced.

[0021] Other features and advantages of the present invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the present invention.

[0022] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A flow chart of an embodiment of a method for determining a parameter range of the present invention;

[0024] Figure 2 It is a structural schematic diagram of an embodiment of a device for determining a parameter range of the present invention;

[0025] Figure 3 is a system architecture diagram of the numerical control system of the present invention;

[0026] Figure 4 A flow chart of another embodiment of a method for determining a parameter range of the present invention;

[0027] Figure 5 It is a flow chart of the genetic algorithm of the present invention.

[0028] In conjunction with the accompanying drawings, the reference numerals in the embodiments of the present invention are as follows:

[0029] 102-acquisition unit; 104-optimization unit. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0031] According to an embodiment of the present invention, a method for determining a parameter range is provided, wherein the parameter is a parameter input to a numerical control system, such as a feed speed, a spindle speed, and the like.

[0032] The structure of the CNC system is as follows Figure 3 As shown, the real-time monitoring module is used to monitor the operation data of the CNC system during operation, and feed the operation data back to the genetic algorithm module. The genetic algorithm module determines the relevant parameters of the genetic algorithm based on the operation data, including population size, crossover probability, mutation probability, selection mechanism, and stop condition, and then saves these parameters in the parameter database for use. The parameter database also stores the preset input range of the input parameters and the initial state data of the equipment.

[0033] When the user operates and starts the CNC system through the interface, the genetic algorithm module obtains the preset input range of the input parameters and the initial state data of the equipment from the parameter database, and determines the relevant parameters of the genetic algorithm according to the operation data. After that, the genetic algorithm module calculates the new input range of the input parameters according to the preset input range of the input parameters, the initial state data of the equipment, and the relevant parameters of the genetic algorithm, and saves the new input range in the database. The data system uses the new input range as the current input range of the input parameters. When the genetic algorithm module calculates a new input range again, the input range stored in the database is used as the preset input range.

[0034] like Figure 1 The flow chart of an embodiment of the method of the present invention is shown in FIG. The parameter range determination method may include: step S110 to step S130.

[0035] In step S110, after the numerical control system is started, the real-time operation data of the numerical control system and the preset input range of the parameter are obtained.

[0036] The CNC system is equipped with sensors and data acquisition modules to continuously collect real-time operation data during the processing, including processing parameters, equipment operation status data, and environmental data. Processing parameters include cutting speed, feed rate, cutting depth, tool status, etc. Equipment operation status includes equipment temperature, vibration frequency, wear rate, etc. Equipment includes machine tool spindles, tools, etc. Environmental data includes ambient temperature and humidity, etc.

[0037] In step S120, the real-time operation data and the preset input range of the parameter are brought into a preset genetic algorithm model to obtain the target input range of the parameter.

[0038] In step S130, the input range of the parameter in the numerical control system is set as the target input range.

[0039] Genetic algorithms have high global search capabilities and the ability to handle complex nonlinear relationships. They can consider multi-factor and multi-objective optimization, and thus determine the optimal parameter input range based on the system's real-time operating data. This can reduce the risk of inappropriate or incorrect system parameter input, avoid machine tool collisions, and solve the problems of reduced machining accuracy, increased equipment wear, and low production efficiency caused by improper parameter settings. This improves machining accuracy, reduces equipment wear, extends equipment life, and reduces production costs.

[0040] In some embodiments, in step S120, the real-time operation data and the preset input range of the parameter are brought into a preset genetic algorithm model to obtain the specific process of the target input range of the parameter, including: steps S210 to S240.

[0041] Step S210: Encode the parameters in the preset genetic algorithm model using the real-time operation data, and define the fitness function of the preset genetic algorithm model using the real-time operation data.

[0042] Coding is to encode the key parameters of the CNC system into the genes of chromosomes. In the genetic algorithm module, the decision variables and encoding methods are first determined, such as the cutting speed, feed rate, cutting depth, etc. in the real-time operation data as decision variables.

[0043] These decision variables are then encoded in binary form. Taking cutting speed as an example, assuming that the range of cutting speed is [Vmin, Vmax], this range can be divided into a certain number of intervals, and each interval can be represented by a binary string. For example, if the length of the binary string is determined to be n bits, then a total of 2 n For cutting speed, the actual speed change represented by each binary bit can be calculated based on its value range and the length of the binary string.

[0044] The fitness function is used to evaluate the optimization effect of each individual in the population. The fitness function can comprehensively consider multiple indicators such as processing accuracy, equipment wear, and production efficiency, so that the parameter input range selected by the genetic algorithm is optimal.

[0045] Step S220: generating an initial population according to a preset input range of the parameter.

[0046] The initial population is randomly generated according to the preset input range. Each individual represents a set of parameter input ranges. The size of the initial population is determined by the population size parameter, which is determined by the genetic algorithm module based on the system's operating data.

[0047] Step S230, performing genetic operations using the fitness function and the initial population to obtain a final population.

[0048] Genetic operations include selection, crossover, and mutation. Each genetic operation will result in a new population until the number of repeated iterations of the genetic operation reaches the maximum, and the last population is the final population.

[0049] In some implementations, in step S230, the specific process of performing genetic operations using the fitness function and the initial population to obtain the final population includes: steps S310 to S350.

[0050] Step S310: using the fitness function to evaluate the fitness value of each individual in the initial population.

[0051] Step S320 , selecting a parent individual from the initial population according to a preset selection strategy and the fitness value of each individual in the initial population.

[0052] Selection strategies include roulette wheel selection or elite selection, etc. The fitness of each individual is evaluated according to the fitness function, and the excellent individuals are selected as the parent individuals and enter the crossover operation.

[0053] Step S330, performing a crossover operation on the parent individuals using a preset crossover probability to obtain a child population; the child population includes at least one new individual.

[0054] For the selected parent individuals, a single-point crossover or multi-point crossover method is used to generate several new individuals. Several new individuals form a new population, and then the new population is mutated. The crossover probability determines the probability of generating a new individual when two individuals cross.

[0055] Step S340: performing a mutation operation on the new individuals in the offspring population using a preset mutation probability.

[0056] Mutating new individuals can improve the diversity of the population. The probability of mutation determines the probability of individual gene mutation. The crossover probability and mutation probability can be dynamically adjusted according to the diversity of the population to avoid premature convergence or low search efficiency.

[0057] Step S350, determining the offspring population after the mutation operation as the final population.

[0058] After the mutation operation, the population composed of all new individuals is determined as the final population, including mutated individuals and non-mutated individuals.

[0059] In some embodiments, the process of iterating the genetic operation is also included, specifically including: performing the iterative operation until the number of iterations is equal to the preset maximum number of iterations; the iterative operation is to determine the final population as the new initial population, and use the fitness function and the new initial population to iteratively perform the genetic operation to obtain the final population.

[0060] In genetic algorithms, genetic operations are performed repeatedly, that is, the three steps of selecting parent individuals, crossover operations, and mutation operations are repeated. Each execution completes an iteration until the preset number of iterations is reached, and the new individuals after the last mutation operation are determined as the final population for fitness evaluation.

[0061] Step S240: performing fitness evaluation on the final population to obtain a target input range of the parameter.

[0062] In the final population, each individual is the target input range of the parameter, and the optimal parameter input range is selected by evaluating the fitness of each individual.

[0063] In some embodiments, in step S240, the specific process of performing fitness evaluation on the final population to obtain the target input range of the parameter includes: using the fitness function to evaluate the fitness value of each individual in the final population; and taking the individual with the highest fitness value in the final population as the target input range of the parameter.

[0064] Taking the feed speed and spindle speed of the CNC system as an example, the steps for determining the target input range of the feed speed and spindle speed using the genetic algorithm are as follows:

[0065] (1) Set the initial parameter range. According to experience and preliminary tests, set the feed speed and spindle speed range, such as feed speed: 100mm / min ~ 500mm / min, spindle speed: 1000rpm ~ 5000rpm.

[0066] (2) Install displacement sensors, force sensors, temperature sensors, etc. at key locations of CNC machine tools to collect data during the processing in real time. The collected data includes feed speed, spindle speed, processing time, tool wear, surface roughness, temperature change, and the collected data is stored in a database.

[0067] (3) Define the fitness function: The fitness function is set to evaluate the quality of the parameter combination. For example, machining time, surface roughness, and tool life are used as evaluation indicators. The evaluation is performed by the time required to machine a workpiece, the smoothness of the machined surface, and the degree of tool wear.

[0068] (4) Generate an initial population: Generate a set of parameter combinations randomly as the initial population, such as feed speed: [100, 200, 300, 400, 500] mm / min, spindle speed: [1000, 2000, 3000, 4000, 5000] rpm.

[0069] (5) Selecting parent individuals from the initial population: For a certain parameter combination in the initial population, such as feed speed 300 mm / min and spindle speed 3000 rpm, calculate the processing time, surface roughness and tool life corresponding to this parameter combination, and then select the top 30% individuals with the highest fitness as the parent individuals.

[0070] (6) Crossover operation: Partially exchange the parameters of two excellent individuals in the parent generation to obtain a new individual.

[0071] (7) Mutation operation: Randomly change the value of a parameter in the new individual. If the optimal solution of the feed speed in a certain generation is concentrated between 300 mm / min and 400 mm / min, the next search range can be narrowed to this interval. Then, the optimal parameter combination of each generation is applied to the CNC system, and its performance is continuously monitored. A closed-loop control is formed, and the parameters are continuously adjusted to gradually approach the global optimal solution.

[0072] By optimizing the input parameter range of the CNC system, the processing time can be reduced, the production efficiency can be improved, the downtime and debugging time caused by improper parameters can be reduced, the surface quality of the processed parts can be improved, the qualification rate can be increased, the wear of the tool can be reduced, and the service life of the tool can be extended.

[0073] In some embodiments, the process of judging the parameters input by the user is also included, specifically including: when inputting the parameters into the input numerical control system, judging whether the input parameters are within the target input range; if the input parameters are not within the target input range, issuing a prompt message that the parameters are out of the set range.

[0074] After the optimal parameter range obtained by the genetic algorithm is fed back to the data system, the parameter input setting range is automatically updated in real time. When the parameters entered by the user are not within the range, a corresponding reminder is issued to ensure that the processing process runs within the optimal range.

[0075] The system interface can display parameter status and range adjustment information in real time, including current parameter value, setting range, adjustment trajectory, etc., as well as abnormal indications of the processing process and instructions for suggesting manual adjustment of the range, so that users can monitor and adjust the processing status easily.

[0076] Figure 4 FIG. 1 is a flow chart of another embodiment of the method for determining the parameter range of the present invention, as shown in FIG. Figure 4 As shown, the method includes:

[0077] Step 1: When the CNC system is started, the preset parameter input limit range and equipment initial state data are loaded from the database, and the parameters of the genetic algorithm are initialized according to the loaded range and data.

[0078] Step 2: Monitor and collect the data of the CNC system during operation in real time, including processing parameters, equipment status, and environmental data.

[0079] Step 3: Input the collected system runtime data into the genetic algorithm, perform parameter encoding, and define the fitness function.

[0080] Step 4: Use the genetic algorithm to calculate the new input limit range of the parameter, update it to the CNC system, and display it on the user interface.

[0081] Step 5: When the parameters input by the user exceed the new input limit range, a corresponding warning is issued.

[0082] Figure 5 is a flow chart of the genetic algorithm of the present invention, as Figure 5 As shown in Figure 1, the process of genetic algorithm includes:

[0083] Step 11, using the preset parameter input restriction range loaded from the database for initialization to obtain an initial population.

[0084] Step 12, select parent individuals from the initial population.

[0085] Step 13, perform a crossover operation on the parent individuals to generate a number of new individuals.

[0086] Step 14, performing mutation operations on the generated new individuals.

[0087] Step 15, evaluate the fitness of several new individuals, and select the individual with the highest fitness as the new input limit range of the parameter.

[0088] By adopting the technical solution of this embodiment, after the CNC system is started, the real-time operation data of the CNC system and the preset input range of the parameters are brought into the genetic algorithm model to determine the target input range of the parameters. Thus, by using the genetic algorithm to optimize the parameter range of the CNC system, the rationality and adaptability of the parameter setting are ensured, the processing accuracy is improved, the production efficiency is increased, and the equipment wear is reduced.

[0089] According to an embodiment of the present invention, a parameter range determination device corresponding to the parameter range determination method is also provided. The parameter is a parameter input to the numerical control system, such as feed speed, spindle speed, etc.

[0090] The structure of the CNC system is as follows Figure 3 As shown, the real-time monitoring module is used to monitor the operation data of the CNC system during operation, and feed the operation data back to the genetic algorithm module. The genetic algorithm module determines the relevant parameters of the genetic algorithm based on the operation data, including population size, crossover probability, mutation probability, selection mechanism, and stop condition, and then saves these parameters in the parameter database for use. The parameter database also stores the preset input range of the input parameters and the initial state data of the equipment.

[0091] When the user operates and starts the CNC system through the interface, the genetic algorithm module obtains the preset input range of the input parameters and the initial state data of the equipment from the parameter database, and determines the relevant parameters of the genetic algorithm according to the operation data. After that, the genetic algorithm module calculates the new input range of the input parameters according to the preset input range of the input parameters, the initial state data of the equipment, and the relevant parameters of the genetic algorithm, and saves the new input range in the database. The data system uses the new input range as the current input range of the input parameters. When the genetic algorithm module calculates a new input range again, the input range stored in the database is used as the preset input range.

[0092] See also Figure 2 The structure diagram of an embodiment of the device of the present invention is shown in FIG. The device for determining the parameter range may include: an acquisition unit 102 and an optimization unit 104 .

[0093] The acquisition unit 102 is configured to acquire the real-time operation data of the numerical control system and the preset input range of the parameter after the numerical control system is started.

[0094] The CNC system is equipped with sensors and data acquisition modules to continuously collect real-time operation data during the processing, including processing parameters, equipment operation status data, and environmental data. Processing parameters include cutting speed, feed rate, cutting depth, tool status, etc. Equipment operation status includes equipment temperature, vibration frequency, wear rate, etc. Equipment includes machine tool spindles, tools, etc. Environmental data includes ambient temperature and humidity, etc.

[0095] The optimization unit 104 is configured to bring the real-time operation data and the preset input range of the parameter into a preset genetic algorithm model to obtain the target input range of the parameter.

[0096] The optimization unit 104 is further configured to set the input range of the parameter in the numerical control system as the target input range.

[0097] Genetic algorithms have high global search capabilities and the ability to handle complex nonlinear relationships. They can consider multi-factor and multi-objective optimization, and thus determine the optimal parameter input range based on the system's real-time operating data. This can reduce the risk of inappropriate or incorrect system parameter input, avoid machine tool collisions, and solve the problems of reduced machining accuracy, increased equipment wear, and low production efficiency caused by improper parameter settings. This improves machining accuracy, reduces equipment wear, extends equipment life, and reduces production costs.

[0098] In some implementations, the optimization unit 104 brings the real-time operation data and the preset input range of the parameter into a preset genetic algorithm model to obtain a specific process of the target input range of the parameter, including:

[0099] The optimization unit 104 is specifically configured to encode the parameters in the preset genetic algorithm model using the real-time operation data, and to define the fitness function of the preset genetic algorithm model using the real-time operation data.

[0100] Coding is to encode the key parameters of the CNC system into the genes of chromosomes. In the genetic algorithm module, the decision variables and encoding methods are first determined, such as the cutting speed, feed rate, cutting depth, etc. in the real-time operation data as decision variables.

[0101] These decision variables are then encoded in binary form. Taking cutting speed as an example, assuming that the range of cutting speed is [Vmin, Vmax], this range can be divided into a certain number of intervals, and each interval can be represented by a binary string. For example, if the length of the binary string is determined to be n bits, then a total of 2 n For cutting speed, the actual speed change represented by each binary bit can be calculated based on its value range and the length of the binary string.

[0102] The fitness function is used to evaluate the optimization effect of each individual in the population. The fitness function can comprehensively consider multiple indicators such as processing accuracy, equipment wear, and production efficiency, so that the parameter input range selected by the genetic algorithm is optimal.

[0103] The optimization unit 104 is specifically configured to generate an initial population according to a preset input range of the parameter.

[0104] The initial population is randomly generated according to the preset input range. Each individual represents a set of parameter input ranges. The size of the initial population is determined by the population size parameter, which is determined by the genetic algorithm module based on the system's operating data.

[0105] The optimization unit 104 is specifically configured to perform genetic operations using the fitness function and the initial population to obtain a final population.

[0106] Genetic operations include selection, crossover, and mutation. Each genetic operation will result in a new population until the number of repeated iterations of the genetic operation reaches the maximum, and the last population is the final population.

[0107] In some implementations, the optimization unit 104 uses the fitness function and the initial population to perform genetic operations to obtain a specific process of the final population, including:

[0108] The optimization unit 104 is specifically configured to evaluate the fitness value of each individual in the initial population using the fitness function.

[0109] The optimization unit 104 is specifically configured to select a parent individual from the initial population according to a preset selection strategy and the fitness value of each individual in the initial population.

[0110] Selection strategies include roulette wheel selection or elite selection, etc. The fitness of each individual is evaluated according to the fitness function, and the excellent individuals are selected as the parent individuals and enter the crossover operation.

[0111] The optimization unit 104 is specifically configured to perform a crossover operation on the parent individuals using a preset crossover probability to obtain a child population; the child population includes at least one new individual.

[0112] For the selected parent individuals, a single-point crossover or multi-point crossover method is used to generate several new individuals. Several new individuals form a new population, and then the new population is mutated. The crossover probability determines the probability of generating a new individual when two individuals cross.

[0113] The optimization unit 104 is specifically configured to perform a mutation operation on the new individuals in the offspring population using a preset mutation probability.

[0114] Mutating new individuals can improve the diversity of the population. The probability of mutation determines the probability of individual gene mutation. The crossover probability and mutation probability can be dynamically adjusted according to the diversity of the population to avoid premature convergence or low search efficiency.

[0115] The optimization unit 104 is specifically configured to determine the offspring population after the mutation operation as the final population.

[0116] After the mutation operation, the population composed of all new individuals is determined as the final population, including mutated individuals and non-mutated individuals.

[0117] In some embodiments, the optimization unit 104 is further configured to: perform an iterative operation until the number of iterations is equal to a preset maximum number of iterations; the iterative operation is to determine the final population as a new initial population, and iteratively perform genetic operations using the fitness function and the new initial population to obtain the final population.

[0118] In genetic algorithms, genetic operations are performed repeatedly, that is, the three steps of selecting parent individuals, crossover operations, and mutation operations are repeated. Each execution completes an iteration until the preset number of iterations is reached, and the new individuals after the last mutation operation are determined as the final population for fitness evaluation.

[0119] The optimization unit 104 is specifically configured to perform fitness evaluation on the final population to obtain a target input range of the parameter.

[0120] In the final population, each individual is the target input range of the parameter, and the optimal parameter input range is selected by evaluating the fitness of each individual.

[0121] In some embodiments, the optimization unit 104 performs fitness evaluation on the final population to obtain the specific process of the target input range of the parameter, including: using the fitness function to evaluate the fitness value of each individual in the final population; and taking the individual with the highest fitness value in the final population as the target input range of the parameter.

[0122] Taking the feed speed and spindle speed of the CNC system as an example, the steps to determine the target input range of the feed speed and spindle speed using the genetic algorithm are as follows:

[0123] (1) Set the initial parameter range. According to experience and preliminary tests, set the feed speed and spindle speed range, such as feed speed: 100mm / min ~ 500mm / min, spindle speed: 1000rpm ~ 5000rpm.

[0124] (2) Install displacement sensors, force sensors, temperature sensors, etc. at key locations of CNC machine tools to collect data during the processing in real time. The collected data includes feed speed, spindle speed, processing time, tool wear, surface roughness, temperature change, and the collected data is stored in a database.

[0125] (3) Define the fitness function: The fitness function is set to evaluate the quality of the parameter combination. For example, machining time, surface roughness, and tool life are used as evaluation indicators. The evaluation is performed by the time required to machine a workpiece, the smoothness of the machined surface, and the degree of tool wear.

[0126] (4) Generate an initial population: Generate a set of parameter combinations randomly as the initial population, such as feed speed: [100, 200, 300, 400, 500] mm / min, spindle speed: [1000, 2000, 3000, 4000, 5000] rpm.

[0127] (5) Selecting parent individuals from the initial population: For a certain parameter combination in the initial population, such as feed speed 300 mm / min and spindle speed 3000 rpm, calculate the processing time, surface roughness and tool life corresponding to this parameter combination, and then select the top 30% individuals with the highest fitness as the parent individuals.

[0128] (6) Crossover operation: Partially exchange the parameters of two excellent individuals in the parent generation to obtain a new individual.

[0129] (7) Mutation operation: Randomly change the value of a parameter in the new individual. If the optimal solution of the feed speed in a certain generation is concentrated between 300 mm / min and 400 mm / min, the next search range can be narrowed to this interval. Then, the optimal parameter combination of each generation is applied to the CNC system, and its performance is continuously monitored. A closed-loop control is formed, and the parameters are continuously adjusted to gradually approach the global optimal solution.

[0130] By optimizing the input parameter range of the CNC system, the processing time can be reduced, the production efficiency can be improved, the downtime and debugging time caused by improper parameters can be reduced, the surface quality of the processed parts can be improved, the qualification rate can be increased, the wear of the tool can be reduced, and the service life of the tool can be extended.

[0131] In some embodiments, the optimization unit 104 is further configured to: when inputting the parameter into the input numerical control system, determine whether the input parameter is within the target input range; if the input parameter is not within the target input range, issue a prompt message indicating that the parameter exceeds the set range.

[0132] After the optimal parameter range obtained by the genetic algorithm is fed back to the data system, the parameter input setting range is automatically updated in real time. When the parameters entered by the user are not within the range, a corresponding reminder is issued to ensure that the processing process runs within the optimal range.

[0133] The system interface can display parameter status and range adjustment information in real time, including current parameter value, setting range, adjustment trajectory, etc., as well as abnormal indications of the processing process and instructions for suggesting manual adjustment of the range, so that users can monitor and adjust the processing status easily.

[0134] Figure 4 FIG. 1 is a flow chart of another embodiment of the method for determining the parameter range of the present invention, as shown in FIG. Figure 4 As shown, the method includes:

[0135] Step 1: When the CNC system is started, the preset parameter input limit range and equipment initial state data are loaded from the database, and the parameters of the genetic algorithm are initialized according to the loaded range and data.

[0136] Step 2: Monitor and collect the data of the CNC system during operation in real time, including processing parameters, equipment status, and environmental data.

[0137] Step 3: Input the collected system runtime data into the genetic algorithm, perform parameter encoding, and define the fitness function.

[0138] Step 4: Use the genetic algorithm to calculate the new input limit range of the parameter, update it to the CNC system, and display it on the user interface.

[0139] Step 5: When the parameters input by the user exceed the new input limit range, a corresponding warning is issued.

[0140] Figure 5 is a flow chart of the genetic algorithm of the present invention, as Figure 5 As shown in Figure 1, the process of genetic algorithm includes:

[0141] Step 11, using the preset parameter input restriction range loaded from the database for initialization to obtain an initial population.

[0142] Step 12, select parent individuals from the initial population.

[0143] Step 13, perform a crossover operation on the parent individuals to generate a number of new individuals.

[0144] Step 14, performing mutation operations on the generated new individuals.

[0145] Step 15, evaluate the fitness of several new individuals, and select the individual with the highest fitness as the new input limit range of the parameter.

[0146] Since the processing and functions implemented by the device of this embodiment basically correspond to the embodiments, principles and examples of the aforementioned method, for the details not fully described in this embodiment, please refer to the relevant descriptions in the aforementioned embodiments, and no further elaboration will be made here.

[0147] By adopting the technical solution of the present invention, after the CNC system is started, the real-time operation data of the CNC system and the preset input range of the parameters are brought into the genetic algorithm model to determine the target input range of the parameters. Thus, by using the genetic algorithm to optimize the parameter range of the CNC system, the rationality and adaptability of the parameter setting are ensured, the processing accuracy is improved, the production efficiency is increased, and the equipment wear is reduced.

[0148] According to an embodiment of the present invention, a numerical control system corresponding to the parameter range determination device is also provided. The numerical control system may include: the parameter range determination device described above.

[0149] Since the processing and functions implemented by the numerical control system of this embodiment basically correspond to the embodiments, principles and examples of the aforementioned devices, for the details not fully described in this embodiment, please refer to the relevant descriptions in the aforementioned embodiments and will not be repeated here.

[0150] By adopting the technical solution of the present invention, after the CNC system is started, the real-time operation data of the CNC system and the preset input range of the parameters are brought into the genetic algorithm model to determine the target input range of the parameters. Thus, by using the genetic algorithm to optimize the parameter range of the CNC system, the rationality and adaptability of the parameter setting are ensured, the processing accuracy is improved, the production efficiency is increased, and the equipment wear is reduced.

[0151] According to an embodiment of the present invention, a storage medium corresponding to the parameter range determination method is also provided, wherein the storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the parameter range determination method described above.

[0152] Since the processing and functions implemented by the storage medium of this embodiment basically correspond to the embodiments, principles and examples of the aforementioned method, for the details not fully described in this embodiment, please refer to the relevant descriptions in the aforementioned embodiments, and no further elaboration will be made here.

[0153] By adopting the technical solution of the present invention, after the CNC system is started, the real-time operation data of the CNC system and the preset input range of the parameters are brought into the genetic algorithm model to determine the target input range of the parameters. Thus, by using the genetic algorithm to optimize the parameter range of the CNC system, the rationality and adaptability of the parameter setting are ensured, the processing accuracy is improved, the production efficiency is increased, and the equipment wear is reduced.

[0154] According to an embodiment of the present invention, a computer program product corresponding to the parameter range determination method is also provided. The computer program product includes a computer program. When the computer program product is processed and executed, the steps of the parameter range determination method are implemented.

[0155] Since the processing and functions implemented by the computer program product of this embodiment basically correspond to the embodiments, principles and examples of the aforementioned method, for the details not fully described in this embodiment, please refer to the relevant descriptions in the aforementioned embodiments and will not be repeated here.

[0156] By adopting the technical solution of the present invention, after the CNC system is started, the real-time operation data of the CNC system and the preset input range of the parameters are brought into the genetic algorithm model to determine the target input range of the parameters. Thus, by using the genetic algorithm to optimize the parameter range of the CNC system, the rationality and adaptability of the parameter setting are ensured, the processing accuracy is improved, the production efficiency is increased, and the equipment wear is reduced.

[0157] In summary, it is easy for those skilled in the art to understand that, under the premise of no conflict, the above-mentioned advantageous methods can be freely combined and superimposed.

[0158] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the scope of the claims of the present invention.

Claims

1. A method for determining a parameter range, characterized in that: The parameters are parameters input to the numerical control system; the method comprises: After the numerical control system is started, real-time operation data of the numerical control system and a preset input range of the parameter are obtained; Bringing the real-time operation data and the preset input range of the parameter into a preset genetic algorithm model to obtain a target input range of the parameter; The input range of the parameter in the numerical control system is set as the target input range.

2. The method for determining a parameter range according to claim 1, characterized in that: Bringing the real-time operation data and the preset input range of the parameter into a preset genetic algorithm model to obtain the target input range of the parameter, including: Encoding parameters in a preset genetic algorithm model using the real-time operation data, and defining a fitness function of the preset genetic algorithm model using the real-time operation data; generating an initial population according to a preset input range of the parameter; Performing genetic operations using the fitness function and the initial population to obtain a final population; The fitness of the final population is evaluated to obtain the target input range of the parameter.

3. The method for determining a parameter range according to claim 2, characterized in that: Performing genetic operations using the fitness function and the initial population to obtain a final population includes: Using the fitness function to evaluate the fitness value of each individual in the initial population; Selecting a parent individual from the initial population according to a preset selection strategy and the fitness value of each individual in the initial population; Performing a crossover operation on the parent individuals using a preset crossover probability to obtain a progeny population; the progeny population includes at least one new individual; Performing mutation operations on new individuals in the offspring population using a preset mutation probability; The offspring population after the mutation operation is determined as the final population.

4. The method for determining a parameter range according to claim 3, characterized in that: Also includes: Perform iterative operations until the number of iterations is equal to the preset maximum number of iterations; The iterative operation is to determine the final population as a new initial population, and iteratively perform genetic operations using the fitness function and the new initial population to obtain the final population.

5. The method for determining a parameter range according to any one of claims 2 to 4, characterized in that: Performing fitness evaluation on the final population to obtain a target input range of the parameter includes: Using the fitness function to evaluate the fitness value of each individual in the final population; The individual with the highest fitness value in the final population is used as the target input range of the parameter.

6. The method for determining a parameter range according to claim 1 or 5, characterized in that: Also includes: When inputting the parameter into the input numerical control system, determining whether the input parameter is within the target input range; If the input parameter is not within the target input range, a prompt message indicating that the parameter exceeds the setting range is issued.

7. A device for determining a parameter range, characterized in that: The parameters are parameters input into the numerical control system; the device comprises: an acquisition unit, configured to acquire real-time operation data of the numerical control system and a preset input range of the parameter after the numerical control system is started; an optimization unit, configured to bring the real-time operation data and the preset input range of the parameter into a preset genetic algorithm model to obtain a target input range of the parameter; The optimization unit is further configured to set the input range of the parameter in the numerical control system as the target input range.

8. A numerical control system, characterized in that: include: The parameter range determination device as claimed in claim 7.

9. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the method for determining the parameter range according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images