CN116300475B - Metal rolling control method and system - Google Patents
Metal rolling control method and system Download PDFInfo
- Publication number
- CN116300475B CN116300475B CN202310527955.1A CN202310527955A CN116300475B CN 116300475 B CN116300475 B CN 116300475B CN 202310527955 A CN202310527955 A CN 202310527955A CN 116300475 B CN116300475 B CN 116300475B
- Authority
- CN
- China
- Prior art keywords
- rolling
- adjustment
- quality
- fitness
- parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
- G07C3/14—Quality control systems
- G07C3/143—Finished product quality control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23P—METAL-WORKING NOT OTHERWISE PROVIDED FOR; COMBINED OPERATIONS; UNIVERSAL MACHINE TOOLS
- B23P9/00—Treating or finishing surfaces mechanically, with or without calibrating, primarily to resist wear or impact, e.g. smoothing or roughening turbine blades or bearings; Features of such surfaces not otherwise provided for, their treatment being unspecified
- B23P9/02—Treating or finishing by applying pressure, e.g. knurling
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The application provides a metal rolling control method and a system, which relate to the technical field of data processing, and are used for acquiring M quality parameters and unregulated rolling processes of a target metal part under the condition of not carrying out rolling, carrying out M quality parameter detection based on M quality standards to acquire a basic quality detection result and constructing an adaptability function, randomly generating a plurality of process adjustment modes to carry out process adjustment optimizing, calculating the adaptability and carrying out iterative optimizing to acquire an optimal rolling process to carry out rolling control, solving the technical problems that the conventional metal rolling process is single and has insufficient combination degree with a product to be processed, so that the processing effect is not matched with the application requirement of the product in the prior art, carrying out multi-level adjustment and adaptability calculation optimizing on the initial rolling process of the target metal part, carrying out processing control based on the optimal adjustment process to maximally ensure the processing quality, and improving the adaptability of the processed product and the application requirement.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a metal rolling control method and system.
Background
The metal parts are continuously subjected to cyclic load in operation, so that the surfaces of the parts are subjected to a certain degree of fatigue damage, and potential accident risks exist. The surface plastic deformation can be carried out along with the metal part by the surface rolling strengthening, so that the surface roughness is reduced, and the performance of the part is strengthened. When the metal rolling control is currently performed, the processing control is performed based on pre-configured process parameters, resulting in a lack of processing control effects.
In the prior art, the conventional metal rolling process is single, and the combination degree of the metal rolling process and a product to be processed is insufficient, so that the rolling effect is not matched with the application requirement of the product.
Disclosure of Invention
The application provides a metal rolling processing control method and a system, which are used for solving the technical problem that in the prior art, the processing effect is not matched with the application requirement of a product due to the fact that the conventional metal rolling process is single and the combination degree of the conventional metal rolling process and the product to be processed is insufficient.
In view of the above problems, the present application provides a metal rolling control method and system.
In a first aspect, the present application provides a metal rolling control method, the method comprising:
obtaining M quality parameters of M quality parameter items of a target metal part without rolling, wherein the target metal part is a metal part to be rolled, and M is an integer greater than 1;
acquiring an unadjusted rolling process for rolling the target metal part, wherein the unadjusted rolling process comprises N rolling parameters of N rolling parameter items, and N is an integer greater than 1;
based on M quality standards of the M quality parameter items, detecting the M quality parameters to obtain a basic quality detection result, and constructing an adaptability function according to the basic quality detection result;
randomly generating a plurality of process adjustment modes in N rolling parameter ranges of the N rolling parameter items, wherein each process adjustment mode comprises the step of randomly adjusting at least one random rolling parameter in a random amplitude;
adjusting and optimizing the unadjusted rolling process, calculating fitness according to the fitness function in the optimizing process, and selecting a corresponding number of process adjustment modes according to the fitness to perform iterative optimization;
and after optimizing, obtaining an optimal rolling process, and controlling the rolling process of the target metal part.
In a second aspect, the present application provides a metal rolling control system, the system comprising:
the parameter acquisition module is used for acquiring M quality parameters of M quality parameter items of a target metal part which is to be subjected to rolling processing, wherein M is an integer greater than 1;
the process acquisition module is used for acquiring an unadjusted rolling process for rolling the target metal part, wherein the unadjusted rolling process comprises N rolling parameters of N rolling parameter items, and N is an integer greater than 1;
the function construction module is used for obtaining basic quality detection results for the M quality parameter detection based on M quality standards of the M quality parameter items and constructing an adaptability function according to the basic quality detection results;
the process adjustment module is used for randomly generating a plurality of process adjustment modes within N rolling parameter ranges of the N rolling parameter items, and each process adjustment mode comprises adjustment of random amplitude of at least one random rolling parameter;
the process optimizing module is used for adjusting and optimizing the unadjusted rolling process, calculating the fitness according to the fitness function in the optimizing process, and selecting a corresponding number of process adjusting modes according to the fitness to perform iterative optimizing;
and the process control module is used for obtaining an optimal rolling process after optimizing, and controlling the rolling processing of the target metal part.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
according to the metal rolling control method provided by the embodiment of the application, M quality parameters of M quality parameter items of a target metal part under the condition of not carrying out rolling and an unadjusted rolling process are obtained, wherein the unadjusted rolling process comprises N rolling parameters of N rolling parameter items, and N is an integer larger than 1; based on M quality standards of the M quality parameter items, a basic quality detection result is obtained through detection of the M quality parameters, an adaptability function is constructed, a plurality of process adjustment modes are randomly generated in N rolling parameter ranges of the N rolling parameter items, adjustment and optimization are conducted on the unadjusted rolling process, the adaptability is calculated according to the adaptability function, a corresponding number of process adjustment modes are selected for iterative optimization, an optimal rolling process is obtained, rolling processing control is conducted on the target metal part, the technical problem that in the prior art, due to the fact that a conventional metal rolling process is single, the combination degree of a product to be processed is insufficient, the processing effect is not matched with the application requirement of the product is solved, multi-level adjustment and adaptability calculation optimization are conducted on the initial rolling process of the target metal part, correction and optimization are conducted, processing control is conducted on the basis of the optimal adjustment process, and processing quality is maximized, and the adaptation degree of the processed product and the application requirement is improved.
Drawings
FIG. 1 is a schematic flow chart of a metal rolling control method;
FIG. 2 is a schematic flow chart of a plurality of process adjustment modes in a metal rolling control method;
FIG. 3 is a schematic view of a process fitness calculation flow in a metal rolling control method according to the present application;
fig. 4 is a schematic structural view of a metal rolling control system according to the present application.
Reference numerals illustrate: the system comprises a parameter acquisition module 11, a process acquisition module 12, a function construction module 13, a process adjustment module 14, a process optimizing module 15 and a process control module 16.
Detailed Description
The application provides a metal rolling control method and a system, which are used for obtaining M quality parameters of M quality parameter items of a target metal part under the condition of not rolling and an unadjusted rolling process, detecting the M quality parameters based on M quality standards to obtain a basic quality detection result, constructing an adaptability function, randomly generating a plurality of process adjustment modes to perform process adjustment optimizing, calculating the adaptability and performing iterative optimizing to obtain an optimal rolling process for rolling control, and are used for solving the technical problems in the prior art that the conventional metal rolling process is single, the combination degree with a product to be processed is insufficient, and the processing effect is not matched with the application requirement of the product.
Example 1
As shown in fig. 1, the present application provides a metal rolling control method, which includes:
step S100: obtaining M quality parameters of M quality parameter items of a target metal part without rolling, wherein the target metal part is a metal part to be rolled, and M is an integer greater than 1;
further, the step S100 of the present application further includes:
step S110: acquiring M quality parameter items, wherein the M quality parameter items comprise surface roughness, surface hardness, hardening layer depth and wear resistance parameters;
step S120: and detecting and acquiring M quality parameters of the target metal part according to the M quality parameter items.
In particular, metal parts are subject to cyclic loading continuously during operation, resulting in a degree of fatigue failure of the part surface, leading to a potential risk of accidents. The surface plastic deformation can be carried out along with the metal part by the surface rolling strengthening so as to strengthen the performance of the part. According to the metal rolling processing control method provided by the application, the initial rolling process of the target metal part is subjected to multi-level adjustment and fitness calculation optimization, quality parameter items are used as quality inspection dimensions, adjustment and optimization of the rolling process are performed, and processing control is performed based on the optimal adjustment process, so that the processing quality is ensured to the maximum extent, and the application requirement suitability of the processed part is ensured.
Specifically, the target metal part is a part to be rolled, for example, a gear, a rotating shaft, and the like, and a plurality of evaluation and control indexes representing the surface quality of the target metal part, including surface roughness, surface hardness, depth of a hardened layer, and wear resistance parameters, are obtained and used as the M quality parameter items, wherein M generally refers to the number of the quality parameter items, M is an integer greater than 1, and the specific number is adapted to the target metal part to be rolled, for example, 4.
Before rolling the target metal part, the M quality parameter items are respectively detected and measured, for example, the M quality parameters representing the state of the quality parameter item can be detected based on an interferometry method aiming at the surface roughness, and the M quality parameters are not parameters representing the initial state of the processing of the target metal part.
Step S200: acquiring an unadjusted rolling process for rolling the target metal part, wherein the unadjusted rolling process comprises N rolling parameters of N rolling parameter items, and N is an integer greater than 1;
specifically, based on the fact that a rolling tool applies pressure to the surface of the target metal part, the plastic deformation part remained after elastic deformation of the material is recovered, and therefore the surface deformation of the part is strengthened. And determining an adaptive rolling tool based on the state of the target metal part, wherein a rigid rolling tool is adopted when rolling a planar part, an elastic rolling tool is adopted when rolling a curved part, an unadjusted rolling process, such as a vibration rolling process, a warm rolling process and the like, suitable for the target metal part is obtained, configuration parameters of N rolling parameter items are determined, the rolling parameter items comprise rolling pressure, rolling speed, rolling times, rolling interference, feeding quantity and other processing control directions, specific item control values, such as rolling pressure, transformation data and the like, in the unadjusted rolling process for rolling the target metal part in the prior art are determined, and the N rolling parameters are initial rolling control parameters and provide basis for subsequent process adjustment optimization.
Step S300: based on M quality standards of the M quality parameter items, detecting the M quality parameters to obtain a basic quality detection result, and constructing an adaptability function according to the basic quality detection result;
further, based on the M quality criteria of the M quality parameter items, a basic quality detection result is obtained for the M quality parameter detection, and an fitness function is constructed according to the basic quality detection result, and step S300 of the present application further includes:
step S310: acquiring the M quality standards;
step S320: detecting the M quality parameters according to the M quality standards to obtain M basic quality detection parameters serving as the basic quality detection results;
step S330: and constructing the fitness function according to the M basic quality detection parameters, wherein the fitness function comprises the following formula:
wherein Y is the fitness of adjusting the rolling process, < >>And->For the surface roughness and hardness of the jth point of the target metal part surface after being processed by adopting the rolling process, T is the total number of measuring points, < >>As a basic surface roughness quality detection parameter, +.>The hardness quality detection parameters are the hardness depth and the wear resistance parameters of the target metal part processed by adopting the rolling process, and D and G are the hardness depth and the wear resistance parameters of the target metal part processed by adopting the rolling process>For the basic hardening layer depth quality detection parameter and the basic wear-resistant quality detection parameter, < ->、/>、/>And->Is the weight.
Specifically, the critical quality parameters for defining the quality qualification of the target metal part can be determined according to related industry standards, for example, the critical quality parameters can be determined as the M quality standards, or can be directly determined based on the production specification of the target metal part. Mapping and corresponding the M quality parameters and the M quality standards, respectively calculating the ratio of the quality parameters to the quality standards based on the mapping results, taking the ratio of the surface roughness quality parameters to the surface roughness quality standards as basic surface roughness quality detection parameters, respectively calculating and obtaining basic hardness quality detection parameters, basic hardening layer depth quality detection parameters and basic wear-resistant quality detection parameters, and taking the M basic quality detection results as characterization data for measuring the difference between the quality parameters and the quality standards.
Further, the fitness function is constructed based on the M basic quality detection results, the fitness function is a self-built judgment measurement basis for process adjustment optimization, and the fitness formula is expressed as:wherein Y is the fitness of adjusting the rolling process, < >>And->For adjusting the surface roughness and hardness of the j-th point on the surface of the target metal part after the rolling process is adopted, T is the total number of measurement points, +.>As a basic surface roughness quality detection parameter, +.>D and G are the adjustment rollers used as basic hardness quality detection parametersDepth of hardened layer and wear resistance parameters of the target metal part after pressing process machining, +.>For the basic hardening layer depth quality detection parameter and the basic wear-resistant quality detection parameter, < ->、/>、/>And->Is the weight. After processing for the adjustment process, testing the surface roughness and hardness at a plurality of points, for example testing the Rockwell hardness, determining +.>And->The method comprises the steps of carrying out a first treatment on the surface of the The average hardened layer depth and the wear resistance of the target metal part are tested, D and G are determined, the related test method can be determined based on the quality detection method of the target metal part, and the specific weight configuration is subjected to self-defining setting according to the application importance degree of each quality parameter to the target metal part, for example->、/>0.3%>And->At 0.2, the parameters can be obtained directly by detection statistics.
Step S400: randomly generating a plurality of process adjustment modes in N rolling parameter ranges of the N rolling parameter items, wherein each process adjustment mode comprises the step of randomly adjusting at least one random rolling parameter in a random amplitude;
step S500: adjusting and optimizing the unadjusted rolling process, calculating fitness according to the fitness function in the optimizing process, and selecting a corresponding number of process adjustment modes according to the fitness to perform iterative optimization;
step S600: and after optimizing, obtaining an optimal rolling process, and controlling the rolling process of the target metal part.
Specifically, parameter range definition is performed for the N rolling parameter items, and the N rolling parameter ranges are determined for performing parameter adjustment amplitude limitation. Randomly setting a plurality of preset adjustment amplitudes, performing amplitude modulation control on the N rolling parameters, determining N rolling parameter adjustment mode sets, randomly extracting a rolling parameter adjustment mode combination for at least one of the N rolling adjustment parameter items for a plurality of times, and determining the process adjustment modes. And randomly extracting process adjustment modes with preset adjustment quantity based on the process adjustment modes, adjusting and detecting quality of an unadjusted rolling process, determining quality detection results based on M quality parameter items, inputting the quality detection results into the fitness function, performing fitness calculation, selecting the process adjustment mode of the adjusted rolling process with the highest fitness, performing tabu list addition, performing process adjustment and iterative optimization again, repeating for a plurality of times until reaching preset optimization conditions, determining the adjusted rolling process with the highest global fitness, performing rolling control based on the optimal rolling process as the optimal rolling process, and ensuring that the quality of the processing control is matched with the requirements.
Further, as shown in fig. 2, in the N rolling parameter ranges of the N rolling parameter items, a plurality of process adjustment modes are randomly generated, and step S400 of the present application further includes:
step S410: randomly acquiring a plurality of preset adjustment amplitudes;
step S420: forming N rolling parameter adjustment mode sets within the N rolling parameter ranges according to the preset adjustment amplitudes;
step S430: and randomly selecting one rolling parameter adjustment mode from a plurality of rolling parameter adjustment mode sets for a plurality of times to form a process adjustment mode, and obtaining a plurality of process adjustment modes, wherein the number of the plurality of rolling parameter adjustment modes is more than or equal to 1 and less than or equal to N.
Specifically, the control range of the N rolling parameter items is defined, including an upper limit and a lower limit of the rolling parameter items, and the N rolling parameter ranges are further randomly set with the preset adjustment ranges, for example, the preset adjustment ranges of the rolling parameter items may be different by adjusting the preset adjustment ranges of 1%,5%,10%,20% and the like of one rolling parameter. And respectively adjusting the N rolling parameter items based on a plurality of corresponding preset adjustment amplitudes within the rolling parameter range, and performing mapping attribution integration of the N rolling parameter items as a plurality of alternative adjustment modes to generate the N rolling adjustment mode sets. Further, one rolling adjustment mode is selected randomly from a plurality of rolling adjustment mode sets selected randomly for combination for multiple times, wherein the number of the rolling adjustment modes is more than or equal to 1 and less than or equal to N, randomness of the determined rolling adjustment modes can be guaranteed to the greatest extent, the process adjustment modes determined by combination are integrated to be used as the process adjustment modes, the process adjustment modes are alternative process adjustment modes to be subjected to optimizing screening, and parameter adjustment of any amplitude is carried out on any number of rolling parameter items in each process adjustment mode.
Furthermore, the unadjusted rolling process is adjusted and optimized, in the optimizing process, the fitness is calculated according to the fitness function, and a corresponding number of process adjustment modes are selected according to the fitness to perform optimizing, and the step S500 of the application further comprises:
step S510: acquiring a preset adjustment quantity Q, selecting a process adjustment mode of the preset adjustment quantity Q from the plurality of process adjustment modes, adjusting the unadjusted rolling process, and constructing a first neighborhood of the unadjusted rolling process, wherein the first neighborhood comprises Q adjustment rolling processes, and Q is an integer larger than 1;
step S520: calculating the fitness of Q adjustment rolling processes in the first neighborhood based on the fitness function to obtain Q fitness;
step S530: according to the Q fitness, obtaining Q iteration adjustment quantity, obtaining a first optimal adjustment rolling process corresponding to the maximum value in the Q fitness, adding a process adjustment mode for obtaining the first optimal adjustment rolling process through adjustment into a tabu table, wherein the process adjustment mode cannot be used in tabu iteration times, and deleting the process adjustment mode from the tabu table after the tabu iteration times;
step S540: according to the Q iteration adjustment quantity, randomly selecting process adjustment modes of the Q iteration adjustment quantity from the process adjustment modes, respectively adjusting the Q adjustment rolling processes, constructing Q second neighborhoods, and carrying out iteration optimization;
step S550: and continuing iteration until a preset optimizing condition is reached, and outputting an adjusting rolling process with the maximum adaptability in the iterative optimizing process to obtain the optimal rolling process.
Further, as shown in fig. 3, based on the fitness function, fitness of Q adjustment rolling processes in the first neighborhood is calculated, and step S520 of the present application further includes:
step S521: respectively judging whether the Q adjustment rolling processes exist in the historical rolling processing data according to the historical rolling processing data in the preset historical time range of the target metal part;
step S522: if yes, acquiring historical rolling processing quality detection results according to the historical rolling processing data and the M quality parameter items, and calculating and acquiring fitness according to the fitness function;
step S523: if not, adopting an adjustment rolling process to carry out trial rolling processing of the target metal part, obtaining a rolling processing quality detection result according to the M quality parameter items, and calculating according to the fitness function to obtain fitness.
Further, according to the Q fitness degrees, Q iteration adjustment numbers are obtained, and step S530 of the present application further includes:
step S531: calculating the average value of the Q fitness values to obtain a fitness average value;
step S532: and calculating the preset adjustment quantity Q according to the ratio of the Q fitness to the fitness mean value to obtain the Q iteration adjustment quantity.
Specifically, the number of alternative processes for preliminary process adjustment optimization is determined, and the preset adjustment number Q, Q generally refers to the number of process adjustment manners, for example, 5 or 10, where a larger Q may increase the iteration efficiency, but also increase the calculation amount of each iteration, which may be set by those skilled in the art. Based on the process adjustment modes, randomly selecting process adjustment modes meeting the preset adjustment quantity Q, adjusting the unadjusted rolling process, integrating the adjusted Q adjustment rolling processes, and forming a first neighborhood of the unadjusted rolling process. And further performing fitness calculation on Q adjustment rolling processes in the first adjacent area based on the fitness function.
Specifically, the suitability detection mode is determined by combining the Q application live conditions of the rolling process, the preset historical time range is set, that is, a time interval bordering the current time node is set in a user-defined manner, for example, the past year or the like, and the historical rolling processing data of the target metal part is called based on the preset historical time range. And processing record searching is carried out by taking the Q adjustment rolling processes as searching directions. If the processing data of the Q rolling process adjustment exist in the historical rolling processing data, the processing data are used as rolling processing quality detection source data, the M quality parameter items are used as quality detection evaluation indexes, and the historical rolling processing quality detection results are determined, wherein the historical rolling processing quality detection results can be directly identified and determined. Inputting the historical rolling processing quality detection result into the fitness function, and calculating and adjusting the fitness of the rolling process; and aiming at the Q adjustment rolling processes which do not exist in the historical rolling data, adopting the adjustment rolling process to perform trial rolling processing on the target metal part, performing quality detection on the M quality parameter items on a rolling processing sample as a rolling processing quality detection result, and further calculating the adaptability of the rolling processing quality detection result based on the adaptability function.
Further, performing fitness integration to obtain the Q fitness values, performing average calculation on the Q fitness values to obtain a fitness average value, respectively calculating the ratio of the Q fitness values to the fitness average value, respectively performing product operation on the preset adjustment quantity Q, and rounding to determine the Q iteration adjustment quantity, where the Q iteration adjustment quantity is the number of adjustable iterative rolling processes based on the Q adjustment rolling processes, and the larger the fitness is, the more the corresponding iterative adjustment quantity is, the more process adjustment modes that can be randomly selected are, and the more offspring adjustment rolling processes can be iteratively generated.
And simultaneously, checking the Q adaptation degrees, determining a first optimal adjustment rolling process corresponding to the maximum adaptation degree, adding a process adjustment mode for adjusting the first optimal adjustment rolling process into a tabu list for locking, taking the Q iteration adjustment numbers as process derivative adjustment amounts of the corresponding process adjustment modes, randomly selecting the process adjustment modes meeting the corresponding iteration adjustment numbers based on the process adjustment modes, respectively carrying out matching corresponding adjustment on the Q adjustment rolling processes, constructing the Q second neighborhoods, wherein the Q second neighborhoods are in one-to-one correspondence with the Q adjustment rolling processes, and comprise a plurality of child adjustment rolling processes corresponding to the adjustment rolling processes, wherein the higher the adaptation degree is, the wider the corresponding second neighborhoods are, the higher the probability of the global optimal rolling process is, and the global optimizing efficiency and the accuracy are improved. And carrying out optimization in the Q second neighborhoods, wherein the specific optimization mode is the same as the above, determining a detection result taking M quality parameter items as a standard based on an adaptive rolling quality detection mode, calculating based on an adaptive function, determining a second optimal adjustment rolling process corresponding to the maximum adaptive degree, adding a process adjustment mode for obtaining the second optimal adjustment rolling process into a tabu table for locking, and carrying out adjustment iteration of the rolling process in the tabu iteration number by using the process adjustment mode until each item in the tabu table gradually deletes from the tabu table after reaching the tabu iteration number respectively, wherein the tabu iteration number is the iteration number of the limited-level optimal adjustment rolling process which is set in a self-defining mode, for example, 2 times, so that the problem of local optimum is avoided. Repeating the optimizing mode to continue optimizing iteration until the preset optimizing condition is reached, namely, the preset iteration times or the number of the adjusting rolling processes generated by iteration reaches a preset value, wherein the preset iteration times can be 20 times, the preset value can be 10000, the adjusting rolling process with the largest global fitness in the optimizing process is determined as the optimal rolling process, and the optimal rolling process is the rolling process with the highest fitness with the target metal part.
Example two
Based on the same inventive concept as one of the metal rolling control methods in the foregoing embodiments, as shown in fig. 4, the present application provides a metal rolling control system including:
a parameter obtaining module 11, where the parameter obtaining module 11 is configured to obtain M quality parameters of M quality parameter items of a target metal part under non-rolling processing, where the target metal part is a metal part to be rolled, and M is an integer greater than 1;
a process acquisition module 12, wherein the process acquisition module 12 is configured to acquire an unadjusted rolling process for rolling the target metal part, the unadjusted rolling process including N rolling parameters of N rolling parameter items, where N is an integer greater than 1;
the function construction module 13 is configured to obtain a basic quality detection result for the M quality parameter detection based on M quality standards of the M quality parameter items, and construct an fitness function according to the basic quality detection result;
a process adjustment module 14, wherein the process adjustment module 14 is configured to randomly generate a plurality of process adjustment modes within N rolling parameter ranges of the N rolling parameter items, and each process adjustment mode includes adjusting at least one random rolling parameter by a random amplitude;
the process optimizing module 15 is used for adjusting and optimizing the unadjusted rolling process, calculating the fitness according to the fitness function in the optimizing process, and selecting a corresponding number of process adjusting modes according to the fitness to perform iterative optimizing;
and the process control module 16 is used for obtaining an optimal rolling process after optimizing the process control module 16 and controlling the rolling processing of the target metal part.
Further, the system further comprises:
the project acquisition module is used for acquiring the M quality parameter projects, wherein the M quality parameter projects comprise surface roughness, surface hardness, hardening layer depth and wear resistance parameters;
and the parameter detection module is used for detecting and acquiring M quality parameters of the target metal part according to the M quality parameter items.
Further, the system further comprises:
the quality standard acquisition module is used for acquiring the M quality standards;
the basic quality detection result acquisition module is used for detecting the M quality parameters according to the M quality standards to obtain M basic quality detection parameters serving as the basic quality detection results;
the fitness function construction module is used for constructing the fitness function according to the M basic quality detection parameters, and the fitness function construction module comprises the following formula:
wherein Y is the fitness of adjusting the rolling process, < >>And->For the surface roughness and hardness of the jth point of the target metal part surface after being processed by adopting the rolling process, T is the total number of measuring points, < >>As a basic surface roughness quality detection parameter, +.>The hardness quality detection parameters are the hardness depth and the wear resistance parameters of the target metal part processed by adopting the rolling process, and D and G are the hardness depth and the wear resistance parameters of the target metal part processed by adopting the rolling process>For the basic hardening layer depth quality detection parameter and the basic wear-resistant quality detection parameter, < ->、/>、/>And->Is the weight.
Further, the system further comprises:
the device comprises a preset adjustment amplitude acquisition module, a control module and a control module, wherein the preset adjustment amplitude acquisition module is used for randomly acquiring a plurality of preset adjustment amplitudes;
the adjustment mode combination module is used for forming N adjustment mode sets of rolling parameters within the N rolling parameter ranges according to the preset adjustment amplitudes;
the process adjustment mode acquisition module is used for randomly selecting one rolling parameter adjustment mode from a plurality of rolling parameter adjustment mode sets for a plurality of times to form a process adjustment mode, and the plurality of process adjustment modes are obtained, wherein the number of the plurality of rolling parameter adjustment modes is more than or equal to 1 and less than or equal to N.
Further, the system further comprises:
the first neighborhood construction module is used for acquiring a preset adjustment quantity Q, selecting a process adjustment mode of the preset adjustment quantity Q from the plurality of process adjustment modes, adjusting the unadjusted rolling process, and constructing a first neighborhood of the unadjusted rolling process, wherein Q adjustment rolling processes are included in the first neighborhood, and Q is an integer larger than 1;
the fitness calculation module is used for calculating the fitness of the Q adjustment rolling processes in the first neighborhood based on the fitness function to obtain Q fitness;
the tabu list adding module is used for obtaining Q iteration adjustment quantities according to the Q fitness, obtaining a first optimal adjustment rolling process corresponding to the maximum value in the Q fitness, adding a process adjustment mode for obtaining the first optimal adjustment rolling process through adjustment into a tabu list, disabling the process adjustment mode in tabu iteration times, and deleting the process adjustment mode from the tabu list after the tabu iteration times;
the second neighborhood construction module is used for randomly selecting process adjustment modes of the Q iteration adjustment quantities from the process adjustment modes according to the Q iteration adjustment quantities, respectively adjusting the Q adjustment rolling processes to construct Q second neighborhoods and carrying out iteration optimization;
and the iterative optimization module is used for continuing iteration until a preset optimization condition is reached, and outputting an adjustment rolling process with the maximum adaptability in the iterative optimization process to obtain the optimal rolling process.
Further, the system further comprises:
the fitness average value calculation module is used for calculating the average value of the Q fitness values to obtain a fitness average value;
the iteration adjustment quantity acquisition module is used for calculating the preset adjustment quantity Q according to the ratio of the Q fitness to the fitness mean value to obtain the Q iteration adjustment quantities.
Further, the system further comprises:
the process judging module is used for respectively judging whether the Q adjustment rolling processes exist in the historical rolling processing data according to the historical rolling processing data in the preset historical time range of the target metal part;
the historical result fitness calculation module is used for acquiring historical rolling quality detection results according to the M quality parameter items and the historical rolling processing data and obtaining fitness according to the fitness function if the historical result fitness calculation module is used for obtaining the fitness according to the historical rolling processing data;
and the trial machining result adaptability calculation module is used for carrying out trial rolling machining on the target metal part by adopting an adjustment rolling process if not, acquiring rolling machining quality detection results according to the M quality parameter items, and calculating according to the adaptability function to obtain the adaptability.
The foregoing detailed description of a metal rolling control method and a metal rolling control system in this embodiment will be apparent to those skilled in the art, and the device disclosed in the embodiments corresponds to the method disclosed in the embodiments, so that the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. A metal rolling control method, the method comprising:
obtaining M quality parameters of M quality parameter items of a target metal part without rolling, wherein the target metal part is a metal part to be rolled, and M is an integer greater than 1;
acquiring an unadjusted rolling process for rolling the target metal part, wherein the unadjusted rolling process comprises N rolling parameters of N rolling parameter items, and N is an integer greater than 1;
based on M quality standards of the M quality parameter items, detecting the M quality parameters to obtain a basic quality detection result, and constructing an adaptability function according to the basic quality detection result;
randomly generating a plurality of process adjustment modes in N rolling parameter ranges of the N rolling parameter items, wherein each process adjustment mode comprises the step of randomly adjusting at least one random rolling parameter in a random amplitude;
adjusting and optimizing the unadjusted rolling process, calculating fitness according to the fitness function in the optimizing process, and selecting a corresponding number of process adjustment modes according to the fitness to perform iterative optimization;
after optimizing, obtaining an optimal rolling process, and controlling rolling processing of the target metal part;
based on M quality standards of the M quality parameter items, a basic quality detection result is obtained for the M quality parameter detection, and an fitness function is constructed according to the basic quality detection result, including:
acquiring the M quality standards;
detecting the M quality parameters according to the M quality standards to obtain M basic quality detection parameters serving as the basic quality detection results;
and constructing the fitness function according to the M basic quality detection parameters, wherein the fitness function comprises the following formula:
wherein Y is the fitness of adjusting the rolling process, < >>And->For the surface roughness and hardness of the jth point of the target metal part surface after being processed by adopting the rolling process, T is the total number of measuring points, < >>As a basic surface roughness quality detection parameter, +.>The hardness quality detection parameters are basic hardness quality detection parameters, D and G are hardening layer depth and wear resistance parameters of the target metal part processed by adopting an adjustment rolling process,is a basic hardening layer depth quality detection parameter and a basic wear-resistant quality detection parameter,is the weight;
adjusting and optimizing the unadjusted rolling process, calculating the fitness according to the fitness function in the optimizing process, and selecting a corresponding number of process adjustment modes according to the fitness to perform optimizing, wherein the method comprises the following steps:
acquiring a preset adjustment quantity Q, selecting a process adjustment mode of the preset adjustment quantity Q from the plurality of process adjustment modes, adjusting the unadjusted rolling process, and constructing a first neighborhood of the unadjusted rolling process, wherein the first neighborhood comprises Q adjustment rolling processes, and Q is an integer larger than 1;
calculating the fitness of Q adjustment rolling processes in the first neighborhood based on the fitness function to obtain Q fitness;
according to the Q fitness, obtaining Q iteration adjustment quantity, obtaining a first optimal adjustment rolling process corresponding to the maximum value in the Q fitness, adding a process adjustment mode for obtaining the first optimal adjustment rolling process through adjustment into a tabu table, wherein the process adjustment mode cannot be used in tabu iteration times, and deleting the process adjustment mode from the tabu table after the tabu iteration times;
according to the Q iteration adjustment quantity, randomly selecting process adjustment modes of the Q iteration adjustment quantity from the process adjustment modes, respectively adjusting the Q adjustment rolling processes, constructing Q second neighborhoods, and carrying out iteration optimization;
and continuing iteration until a preset optimizing condition is reached, and outputting an adjusting rolling process with the maximum adaptability in the iterative optimizing process to obtain the optimal rolling process.
2. The method of claim 1, wherein obtaining M quality parameters for M quality parameter entries for the target metal part without rolling comprises:
acquiring M quality parameter items, wherein the M quality parameter items comprise surface roughness, surface hardness, hardening layer depth and wear resistance parameters;
and detecting and acquiring M quality parameters of the target metal part according to the M quality parameter items.
3. The method of claim 1, wherein randomly generating a plurality of process adjustments over N rolling parameter ranges for the N rolling parameter items comprises:
randomly acquiring a plurality of preset adjustment amplitudes;
forming N rolling parameter adjustment mode sets within the N rolling parameter ranges according to the preset adjustment amplitudes;
and randomly selecting one rolling parameter adjustment mode from a plurality of rolling parameter adjustment mode sets for a plurality of times to form a process adjustment mode, and obtaining a plurality of process adjustment modes, wherein the number of the plurality of rolling parameter adjustment modes is more than or equal to 1 and less than or equal to N.
4. The method of claim 1, wherein obtaining Q iterative adjustment quantities from the Q fitness degrees comprises:
calculating the average value of the Q fitness values to obtain a fitness average value;
and calculating the preset adjustment quantity Q according to the ratio of the Q fitness to the fitness mean value to obtain the Q iteration adjustment quantity.
5. The method of claim 4, wherein calculating fitness of Q adjusted rolling processes in the first neighborhood based on the fitness function comprises:
respectively judging whether the Q adjustment rolling processes exist in the historical rolling processing data according to the historical rolling processing data in the preset historical time range of the target metal part;
if yes, acquiring historical rolling processing quality detection results according to the historical rolling processing data and the M quality parameter items, and calculating and acquiring fitness according to the fitness function;
if not, adopting an adjustment rolling process to carry out trial rolling processing of the target metal part, obtaining a rolling processing quality detection result according to the M quality parameter items, and calculating according to the fitness function to obtain fitness.
6. A metal roll finishing control system, the system comprising:
the parameter acquisition module is used for acquiring M quality parameters of M quality parameter items of a target metal part which is to be subjected to rolling processing, wherein M is an integer greater than 1;
the process acquisition module is used for acquiring an unadjusted rolling process for rolling the target metal part, wherein the unadjusted rolling process comprises N rolling parameters of N rolling parameter items, and N is an integer greater than 1;
the function construction module is used for obtaining basic quality detection results for the M quality parameter detection based on M quality standards of the M quality parameter items and constructing an adaptability function according to the basic quality detection results;
the process adjustment module is used for randomly generating a plurality of process adjustment modes within N rolling parameter ranges of the N rolling parameter items, and each process adjustment mode comprises adjustment of random amplitude of at least one random rolling parameter;
the process optimizing module is used for adjusting and optimizing the unadjusted rolling process, calculating the fitness according to the fitness function in the optimizing process, and selecting a corresponding number of process adjusting modes according to the fitness to perform iterative optimizing;
the process control module is used for obtaining an optimal rolling process after optimizing, and controlling rolling processing of the target metal part;
the function construction module comprises:
the quality standard acquisition module is used for acquiring the M quality standards;
the basic quality detection result acquisition module is used for detecting the M quality parameters according to the M quality standards to obtain M basic quality detection parameters serving as the basic quality detection results;
the fitness function construction module is used for constructing the fitness function according to the M basic quality detection parameters, and the fitness function construction module comprises the following formula:
wherein Y is the fitness of adjusting the rolling process, < >>And->For the surface roughness and hardness of the jth point of the target metal part surface after being processed by adopting the rolling process, T is the total number of measuring points, < >>As a basic surface roughness quality detection parameter, +.>The hardness quality detection parameters are basic hardness quality detection parameters, D and G are hardening layer depth and wear resistance parameters of the target metal part processed by adopting an adjustment rolling process,is a basic hardening layer depth quality detection parameter and a basic wear-resistant quality detection parameter,is the weight;
the process optimizing module comprises:
the first neighborhood construction module is used for acquiring a preset adjustment quantity Q, selecting a process adjustment mode of the preset adjustment quantity Q from the plurality of process adjustment modes, adjusting the unadjusted rolling process, and constructing a first neighborhood of the unadjusted rolling process, wherein Q adjustment rolling processes are included in the first neighborhood, and Q is an integer larger than 1;
the fitness calculation module is used for calculating the fitness of the Q adjustment rolling processes in the first neighborhood based on the fitness function to obtain Q fitness;
the tabu list adding module is used for obtaining Q iteration adjustment quantities according to the Q fitness, obtaining a first optimal adjustment rolling process corresponding to the maximum value in the Q fitness, adding a process adjustment mode for obtaining the first optimal adjustment rolling process through adjustment into a tabu list, disabling the process adjustment mode in tabu iteration times, and deleting the process adjustment mode from the tabu list after the tabu iteration times;
the second neighborhood construction module is used for randomly selecting process adjustment modes of the Q iteration adjustment quantities from the process adjustment modes according to the Q iteration adjustment quantities, respectively adjusting the Q adjustment rolling processes to construct Q second neighborhoods and carrying out iteration optimization;
and the iterative optimization module is used for continuing iteration until a preset optimization condition is reached, and outputting an adjustment rolling process with the maximum adaptability in the iterative optimization process to obtain the optimal rolling process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310527955.1A CN116300475B (en) | 2023-05-11 | 2023-05-11 | Metal rolling control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310527955.1A CN116300475B (en) | 2023-05-11 | 2023-05-11 | Metal rolling control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116300475A CN116300475A (en) | 2023-06-23 |
| CN116300475B true CN116300475B (en) | 2023-08-22 |
Family
ID=86824247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310527955.1A Active CN116300475B (en) | 2023-05-11 | 2023-05-11 | Metal rolling control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116300475B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116892505B (en) * | 2023-09-11 | 2023-12-05 | 华夏天信智能物联股份有限公司 | Intelligent underground pump station liquid supply control method and system |
| CN116954088B (en) * | 2023-09-20 | 2023-12-12 | 南通新丰威机械科技有限公司 | Online monitoring method and system for mixer |
| CN117008480B (en) * | 2023-09-28 | 2023-12-08 | 江苏甬金金属科技有限公司 | Stainless steel product self-adaptive processing control method combined with application scene |
| CN117151657B (en) * | 2023-10-30 | 2024-01-23 | 南通顺裕包装材料有限公司 | Plastic packaging material management method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200270A (en) * | 2014-06-23 | 2014-12-10 | 重庆大学 | Hobbing technological parameter self-adaptive adjusting method based on differential evolution algorithm |
| CN110116254A (en) * | 2019-05-05 | 2019-08-13 | 中国石油天然气集团有限公司 | Oil-gas gathering and transportation composite bimetal pipe girth joint failure prediction and control method |
| CN113176761A (en) * | 2021-04-28 | 2021-07-27 | 西安电子科技大学 | Machine learning-based multi-feature thin plate part quality prediction and process parameter optimization |
| CN113293270A (en) * | 2021-05-21 | 2021-08-24 | 清华大学 | Blade surface ultrasonic rolling reinforcement self-adaptive control system and method |
| CN114676736A (en) * | 2022-05-13 | 2022-06-28 | 浙江工业大学 | Method for predicting surface quality of rolled workpiece |
| CN115310882A (en) * | 2022-10-12 | 2022-11-08 | 北京晨豪科技有限公司 | Visual fire-fighting strategy planning method and system |
| CN115840431A (en) * | 2023-02-27 | 2023-03-24 | 一夫科技股份有限公司 | Production control method and system for II-type anhydrous gypsum |
| CN115903652A (en) * | 2022-11-09 | 2023-04-04 | 苏州富邦机械链传动制造有限公司 | Alignment punching method and system for part machining |
-
2023
- 2023-05-11 CN CN202310527955.1A patent/CN116300475B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200270A (en) * | 2014-06-23 | 2014-12-10 | 重庆大学 | Hobbing technological parameter self-adaptive adjusting method based on differential evolution algorithm |
| CN110116254A (en) * | 2019-05-05 | 2019-08-13 | 中国石油天然气集团有限公司 | Oil-gas gathering and transportation composite bimetal pipe girth joint failure prediction and control method |
| CN113176761A (en) * | 2021-04-28 | 2021-07-27 | 西安电子科技大学 | Machine learning-based multi-feature thin plate part quality prediction and process parameter optimization |
| CN113293270A (en) * | 2021-05-21 | 2021-08-24 | 清华大学 | Blade surface ultrasonic rolling reinforcement self-adaptive control system and method |
| CN114676736A (en) * | 2022-05-13 | 2022-06-28 | 浙江工业大学 | Method for predicting surface quality of rolled workpiece |
| CN115310882A (en) * | 2022-10-12 | 2022-11-08 | 北京晨豪科技有限公司 | Visual fire-fighting strategy planning method and system |
| CN115903652A (en) * | 2022-11-09 | 2023-04-04 | 苏州富邦机械链传动制造有限公司 | Alignment punching method and system for part machining |
| CN115840431A (en) * | 2023-02-27 | 2023-03-24 | 一夫科技股份有限公司 | Production control method and system for II-type anhydrous gypsum |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116300475A (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116300475B (en) | Metal rolling control method and system | |
| El-Taweel et al. | Analysis and optimization of the ball burnishing process through the Taguchi technique | |
| CN106503350B (en) | A kind of design method of spiral bevel gear long-life transmission fatigue reliability | |
| CN106842922B (en) | Numerical control machining error optimization method | |
| CN110906875B (en) | Visual processing method for aperture measurement | |
| CN110222454B (en) | Process design method for milling precision consistency | |
| CN108008006B (en) | Welding seam defect detection method, device, equipment and system | |
| CN110328558B (en) | Milling titanium alloy surface appearance characteristic consistency distribution process control method | |
| Astakhov et al. | Tool life testing in gundrilling: an application of the group method of data handling (GMDH) | |
| Tran et al. | Analysis of the asymmetrical roll bending process through dynamic FE simulations and experimental study | |
| Basak et al. | Experimental research and ANN modeling on the impact of the ball burnishing process on the mechanical properties of 5083 Al-Mg material | |
| CN112101649A (en) | Machining parameter optimization method based on fuzzy entropy weight comprehensive evaluation method-grey correlation analysis method and surface quality evaluation system | |
| CN116026420A (en) | Parameter detection method and system based on bearing machining | |
| CN109341952A (en) | A kind of dynamically balanced dynamic adjustment central hole location degree method of raising engine crankshaft | |
| CN113688458B (en) | Foundation scheme optimization method based on analytic hierarchy process | |
| CN108073074B (en) | Assembly quality control method based on motion characteristics of machine tool feeding system | |
| CN105547170B (en) | A kind of computational methods of the carbide average diameter of bearing steel | |
| CN115982872A (en) | Design method for performance of rolling bearing | |
| Wang et al. | A study on non-uniform deformation of backward flow forming and its influencing factors | |
| CN114139772A (en) | Method for predicting surface quality of workpiece based on optimized generalized regression neural network | |
| CN109766522B (en) | Non-probability reliability sensitivity analysis method for scraper conveyor chain wheel | |
| CN113704922A (en) | Method for predicting surface roughness based on sound vibration and texture features | |
| CN111737825A (en) | Automobile covering part robust design processing method based on high-precision response surface model | |
| CN114818993B (en) | Service life analysis method for hammer mill | |
| Khan et al. | Selection of optimal condition for finishing of centreless-cylindrical ground parts using grey relational and principal component analyses |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |