CN117066337B - Stamping control method and system for motor stator and rotor machining - Google Patents
Stamping control method and system for motor stator and rotor machining Download PDFInfo
- Publication number
- CN117066337B CN117066337B CN202311350642.XA CN202311350642A CN117066337B CN 117066337 B CN117066337 B CN 117066337B CN 202311350642 A CN202311350642 A CN 202311350642A CN 117066337 B CN117066337 B CN 117066337B
- Authority
- CN
- China
- Prior art keywords
- control
- punching
- processing
- stamping
- harmony
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000003754 machining Methods 0.000 title claims description 19
- 238000004080 punching Methods 0.000 claims abstract description 497
- 238000012545 processing Methods 0.000 claims abstract description 352
- 238000004458 analytical method Methods 0.000 claims abstract description 131
- 230000006870 function Effects 0.000 claims abstract description 54
- 238000007418 data mining Methods 0.000 claims abstract description 8
- 238000012360 testing method Methods 0.000 claims description 60
- 238000012549 training Methods 0.000 claims description 27
- 238000005457 optimization Methods 0.000 claims description 20
- 230000006978 adaptation Effects 0.000 claims description 15
- 238000011156 evaluation Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 238000012512 characterization method Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 8
- 238000003475 lamination Methods 0.000 claims 3
- 230000000694 effects Effects 0.000 abstract description 5
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007620 mathematical function Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21D—WORKING OR PROCESSING OF SHEET METAL OR METAL TUBES, RODS OR PROFILES WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21D22/00—Shaping without cutting, by stamping, spinning, or deep-drawing
- B21D22/02—Stamping using rigid devices or tools
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B30—PRESSES
- B30B—PRESSES IN GENERAL
- B30B15/00—Details of, or accessories for, presses; Auxiliary measures in connection with pressing
- B30B15/26—Programme control arrangements
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Manufacture Of Motors, Generators (AREA)
Abstract
The invention discloses a stamping control method and a stamping control system for processing a stator and a rotor of a motor, which relate to the technical field of intelligent control, and the method comprises the following steps: obtaining the processing requirement of a stator and a rotor of a motor; performing punching processing characteristic analysis to generate a punching processing characteristic analysis set; obtaining M stamping control indexes; obtaining first punching processing characteristic information, and obtaining a punching processing control set by data mining; clustering the punching sheet processing control sets based on M punching control indexes to obtain M punching control subsets, performing triggering interval calibration to obtain M punching control triggering intervals, optimizing by combining punching control and acoustic optimizing functions to obtain a first optimal punching control decision, and performing punching control. The invention solves the technical problem of poor stator and rotor punching quality caused by inaccurate control of punching parameters in the prior art, and achieves the technical effect of improving the stator and rotor punching quality by improving the control precision and accuracy of the punching parameters.
Description
Technical Field
The invention relates to the technical field of intelligent control, in particular to a stamping control method and system for machining a stator and a rotor of a motor.
Background
The stator and the rotor of the motor are formed by stacking a plurality of punched sheets, the punched sheets are formed by punching plates, the control of punching parameters of the stator and the rotor of the motor has a critical influence on the quality and the production efficiency of punching parts, but the selection of the punching parameters at present depends on experience values or parameter guiding tables, and the motor has certain limitations, and the control of the parameters such as punching force, temperature and the like is not accurate enough, so that defects such as cracks, burrs and the like appear on finished products, and the quality of the punched sheets is influenced.
Disclosure of Invention
The application provides a stamping control method and system for processing a stator and a rotor of a motor, which are used for solving the technical problem of poor stator and rotor punching quality caused by inaccurate stamping parameter control in the prior art.
In a first aspect of the present application, there is provided a press control method for processing a stator and a rotor of an electric machine, the method comprising: obtaining the processing requirement of a stator and a rotor of a motor; obtaining a ternary punching processing analysis index, wherein the ternary punching processing analysis index comprises a punching processing number index, a punching processing material index and a punching processing structure index; performing punching processing characteristic analysis on the motor stator and rotor processing requirements according to the ternary punching processing analysis index to generate a punching processing characteristic analysis set; obtaining a preset punching control index set, wherein the preset punching control index set comprises M punching control indexes, and M is a positive integer greater than 1; based on the punching processing characteristic analysis set, first punching processing characteristic information is obtained, and data mining is carried out according to the first punching processing characteristic information and the preset punching control index set, so that a punching processing control set is obtained; clustering the punching processing control sets based on the M punching control indexes to obtain M punching control subsets, and executing triggering interval calibration of the M punching control indexes according to the M punching control subsets to obtain M punching control triggering intervals corresponding to the M punching control indexes; optimizing the M stamping control trigger intervals according to a pre-constructed stamping control and sound optimizing function and binary optimizing constraint based on the first stamping processing characteristic information to obtain a first optimal stamping control decision, and executing stamping control of the first stamping processing characteristic information according to the first optimal stamping control decision.
In a second aspect of the present application, there is provided a press control system for processing a stator and a rotor of a motor, the system comprising: the stator and rotor machining requirement acquisition module is used for acquiring the machining requirement of the stator and rotor of the motor; the punching processing analysis index obtaining module is used for obtaining ternary punching processing analysis indexes, wherein the ternary punching processing analysis indexes comprise punching processing number indexes, punching processing material indexes and punching processing structure indexes; the punching processing characteristic analysis module is used for carrying out punching processing characteristic analysis on the motor stator and rotor processing requirements according to the ternary punching processing analysis index to generate a punching processing characteristic analysis set; the device comprises a preset punching control index set obtaining module, a punching control index set processing module and a punching control index set processing module, wherein the preset punching control index set obtaining module is used for obtaining a preset punching control index set, the preset punching control index set comprises M punching control indexes, and M is a positive integer larger than 1; the punching processing control set acquisition module is used for acquiring first punching processing characteristic information based on the punching processing characteristic analysis set, and carrying out data mining according to the first punching processing characteristic information and the preset punching control index set to acquire a punching processing control set; the punching control trigger interval obtaining module is used for clustering the punching processing control sets based on the M punching control indexes to obtain M punching control subsets, and executing trigger interval calibration of the M punching control indexes according to the M punching control subsets to obtain M punching control trigger intervals corresponding to the M punching control indexes; the punching control module is used for optimizing the M punching control trigger intervals according to a pre-constructed punching control and sound optimizing function and binary optimizing constraint based on the first punching processing characteristic information to obtain a first optimal punching control decision, and executing punching control of the first punching processing characteristic information according to the first optimal punching control decision.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
the utility model provides a punching control method for motor stator and rotor processing relates to intelligent control technical field, through carrying out the punching processing characteristic analysis with motor stator and rotor processing demand, generate the punching processing characteristic analysis set, gather punching processing control set, then cluster punching processing control set based on M punching control index, obtain M punching control subset, mark M punching control trigger interval, and combine punching control and sound optimizing function to carry out optimizing, obtain first optimal punching control decision to carry out punching control, the technical problem that the stator and rotor punching quality is poor because punching parameter control is not accurate enough in the prior art has been solved, control accuracy and degree of accuracy through improving punching parameter have been realized, the technological effect of improvement stator and rotor punching quality is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a stamping control method for processing a stator and a rotor of a motor according to an embodiment of the present application;
fig. 2 is a schematic flow chart of generating a feature analysis set for processing a punching sheet in a punching control method for processing a stator and a rotor of a motor according to an embodiment of the present application;
fig. 3 is a schematic flow chart of generating the first optimal stamping control decision in a stamping control method for processing a stator and a rotor of a motor according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a punching control system for processing a stator and a rotor of a motor according to an embodiment of the present application.
Reference numerals illustrate: the device comprises a stator and rotor processing demand acquisition module 11, a punching processing analysis index acquisition module 12, a punching processing characteristic analysis module 13, a preset punching control index set acquisition 14, a punching processing control set acquisition module 15, a punching control trigger interval acquisition module 16 and a punching control module 17.
Detailed Description
The application provides a stamping control method for processing a stator and a rotor of a motor, which is used for solving the technical problem of poor stator and rotor punching quality caused by insufficient precision of stamping parameter control in the prior art.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present application based on the embodiments herein.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, the present application provides a stamping control method for processing a stator and a rotor of a motor, the method comprising:
t10: obtaining the processing requirement of a stator and a rotor of a motor;
specifically, from the product customization demands of target users, the stamping processing demands of the target motor stator and rotor are extracted, wherein the stamping processing demands comprise the technological parameter demands such as stamping shape, quantity, material, thickness, diameter and the like of the motor stator and rotor, and the technological parameter demands are used as references for subsequent stamping control parameter selection.
T20: obtaining a ternary punching processing analysis index, wherein the ternary punching processing analysis index comprises a punching processing number index, a punching processing material index and a punching processing structure index;
optionally, three dimensional processing indexes are extracted through a processing technology of the stator and the rotor of the motor, including a punching processing number index, a punching processing material index and a punching processing structure index, wherein the punching processing structure index is the geometric structure, shape, size and the like of the stator and the rotor of the motor, such as the inner diameter, the outer diameter, the thickness and the like of a stator, and the punching processing number index, the punching processing material index and the punching processing structure index are used together as ternary punching processing analysis indexes which can be used as motor stator and rotor processing requirement analysis indexes of users.
T30: performing punching processing characteristic analysis on the motor stator and rotor processing requirements according to the ternary punching processing analysis index to generate a punching processing characteristic analysis set;
further, as shown in fig. 2, step T30 in the embodiment of the present application further includes:
t31: obtaining a sample punching processing characteristic analysis library, wherein the sample punching processing characteristic analysis library comprises a sample stator and rotor processing requirement record, a sample punching processing number record, a sample punching processing material record and a sample punching processing structure record;
T32: based on a pre-constructed confidence accurate analysis function, constructing a punching processing number analysis layer corresponding to the punching processing number index according to the sample stator and rotor processing requirement record and the sample punching processing number record;
t33: based on the confidence accurate analysis function, constructing a punching processing material analysis layer corresponding to the punching processing material index according to the sample stator and rotor processing requirement record and the sample punching processing material record;
t34: based on the confidence accurate analysis function, constructing a punching processing structure analysis layer corresponding to the punching processing structure index according to the sample stator and rotor processing demand record and the sample punching processing structure record;
t35: integrating the punching processing number analysis layer, the punching processing material analysis layer and the punching processing structure analysis layer to generate a punching processing characteristic analyzer;
t36: and executing the punching processing characteristic analysis of the motor stator and rotor processing requirements according to the punching processing characteristic analyzer to obtain the punching processing characteristic analysis set.
Further, step T30 in the embodiment of the present application further includes:
constructing the confidence accurate analysis function, wherein the confidence accurate analysis function is as follows:
；
Wherein,characterization test confidence coefficient of accuracy,/->Characterization of test accuracy,/->The test error loss rate is characterized.
The method comprises the steps of acquiring a plurality of historical stator and rotor punching data through big data, acquiring a plurality of punching sample data, and constructing a sample punching processing characteristic analysis library, wherein the sample punching processing characteristic analysis library comprises a sample stator and rotor processing requirement record, a sample punching processing number record, a sample punching processing material record and a sample punching processing structure record, and further, constructing a confidence accurate analysis function:the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Characterization test confidence coefficient of accuracy,/->Characterization of test accuracy,/->The test error loss rate is characterized, and the confidence accuracy analysis function is a mathematical function used to describe the degree of confidence of an event or hypothesis.
Further, the processing requirement records of the sample stator and rotor and the processing quantity records of the sample punched sheets are used as training data, a neural network algorithm is combined for supervised training, accuracy verification is carried out by using the confidence accurate analysis function, a punched sheet processing quantity analysis layer corresponding to the punching sheet processing quantity index is obtained and used for analyzing the punching sheet quantity requirement of a target user, and the neural network algorithm is an artificial intelligent algorithm based on a computer simulation neural system operation rule and can simulate learning and recognition mechanisms of human brain and realize intelligent data processing, classification, prediction and other tasks.
And by analogy, taking the record of the processing requirements of the sample stator and the sample rotor and the record of the processing material of the sample punched sheet as training data, combining a neural network algorithm for training, and using the confidence accurate analysis function for accuracy verification to obtain a punched sheet processing material analysis layer corresponding to the index of the processed material of the punched sheet for analyzing the processing material requirement of the punched sheet of a target user; and training by combining the sample stator and rotor processing requirement record and the sample punching processing structure record as training data and a neural network algorithm to obtain a punching processing structure analysis layer corresponding to the punching processing structure index, wherein the punching processing structure analysis layer is used for analyzing the punching processing structure requirement of a target user.
Further, the punching processing number analysis layer, the punching processing material analysis layer and the punching processing structure analysis layer are integrated to form a punching processing characteristic analyzer together and used for determining processing characteristic requirements of the rotor punching.
Further, step T32 in the embodiment of the present application further includes:
t32-1: the processing requirement record of the sample stator and the rotor and the processing quantity record of the sample punching sheet are used as a first construction data sequence, and the first construction data sequence is randomly divided according to a preset division operator to obtain a first training data sequence and a first test data sequence;
T32-2: performing supervised training on the fully-connected neural network according to the first training data sequence to obtain a first punching processing number analyzer;
t32-3: testing the first punching processing number analyzer according to the first test data sequence to obtain a first test accuracy rate and a first test error loss rate;
t32-4: inputting the first test accuracy rate and the first test error loss rate into the confidence accuracy analysis function to obtain a first test confidence accuracy coefficient;
t32-5: judging whether the first test confidence accuracy coefficient meets a preset confidence accuracy interval or not;
t32-6: if the first test confidence accuracy coefficient meets the preset confidence accuracy interval, embedding the first punching processing number analyzer into the punching processing number analysis layer;
t32-7: if the first test confidence accuracy coefficient does not meet the preset confidence accuracy interval, a first loss data sequence is obtained, incremental learning is conducted on the first punching processing number analyzer according to the first loss data sequence until a second punching processing number analyzer meeting the preset confidence accuracy interval is generated, and the second punching processing number analyzer is embedded into the punching processing number analysis layer.
It should be understood that, taking the sample stator and rotor processing requirement record and the sample punching processing number record as the first construction data sequence, presetting a division operator, for example, 7:3, and randomly dividing the first construction data sequence according to the preset division operator, for example, dividing the data quantity of the training data and the test data into a ratio of 7:3, so as to obtain a first training data sequence and a first test data sequence.
Further, the first training data sequence is used for carrying out supervised training on the fully-connected neural network, training data are sequentially input into the fully-connected neural network for training, network parameters are adjusted according to training results until training of all the training data is completed, and the first punching processing number analyzer is obtained. Further, the first punching processing number analyzer is tested by using the first test data sequence, test data are respectively input into the first punching processing number analyzer, the analysis accuracy of the first punching processing number analyzer is calculated according to the consistency of an output result and the test data, the analysis accuracy is used as a first test accuracy, and a first test error loss rate, namely an error rate, is calculated according to the first test accuracy.
Further, the first test accuracy rate and the first test error loss rate are input into the confidence accuracy analysis function, a first test confidence accuracy coefficient is obtained through calculation, whether the first test confidence accuracy coefficient meets a preset confidence accuracy interval is judged, the preset confidence accuracy interval can be set according to an empirical value, if the first test confidence accuracy coefficient meets the preset confidence accuracy interval, the first punching processing number analyzer is embedded into the punching processing number analysis layer, and if the first test confidence accuracy coefficient meets the preset confidence accuracy interval, the first punching processing number analyzer meets accuracy requirements.
Conversely, if the first test confidence accuracy coefficient does not meet the preset confidence accuracy interval, which indicates that the resolution accuracy of the first punching processing number resolver is low, a first loss data sequence, namely a data sequence which is failed in training and cannot be identified by the resolver, is obtained, the first loss data sequence is used as incremental training data, the first punching processing number resolver is subjected to incremental learning, namely incremental training, until a second punching processing number resolver meeting the preset confidence accuracy interval is obtained, and the second punching processing number resolver is embedded into the punching processing number resolution layer to be used as a user punching number demand resolution tool.
T40: obtaining a preset punching control index set, wherein the preset punching control index set comprises M punching control indexes, and M is a positive integer greater than 1;
specifically, according to the stamping process flow of the stator and the rotor of the motor, stamping control indexes including die temperature, stamping force, stamping speed and the like are extracted, and a preset stamping control index set is generated according to the extracted M stamping control indexes and used as a stamping control process optimization index.
T50: based on the punching processing characteristic analysis set, first punching processing characteristic information is obtained, and data mining is carried out according to the first punching processing characteristic information and the preset punching control index set, so that a punching processing control set is obtained;
optionally, the processing characteristics of the target stator or the target rotor are randomly extracted from the processing characteristic analysis set of the punching sheet to serve as first processing characteristic information of the punching sheet, and data mining is performed by referring to the first processing characteristic information of the punching sheet and the preset punching control index set, that is, historical processing data acquisition is performed, and a plurality of sample processing control parameters which are the same as the processing characteristics of the punching sheet of the target stator or the target rotor are acquired, including a die temperature control parameter, a punching force control parameter, a punching speed control parameter and the like, so that a processing control set of the punching sheet is formed.
T60: clustering the punching processing control sets based on the M punching control indexes to obtain M punching control subsets, and executing triggering interval calibration of the M punching control indexes according to the M punching control subsets to obtain M punching control triggering intervals corresponding to the M punching control indexes;
the method comprises the steps of clustering sample control indexes in the punching processing control set by referring to index classification of the M punching control indexes, classifying the same type of control indexes into the same cluster, classifying different types of control indexes into different clusters to obtain M punching control subsets, and calibrating trigger intervals of the M punching control indexes, namely calibrating an adjustment range of the punching indexes, for example, calibrating the trigger intervals of punching speed to be 200-400 times/min, and the like, calibrating M punching control trigger intervals corresponding to the M punching control indexes, wherein the M punching control trigger intervals can be used as optimizing spaces of punching control parameters.
T70: optimizing the M stamping control trigger intervals according to a pre-constructed stamping control and sound optimizing function and binary optimizing constraint based on the first stamping processing characteristic information to obtain a first optimal stamping control decision, and executing stamping control of the first stamping processing characteristic information according to the first optimal stamping control decision.
Further, step T70 of the embodiment of the present application further includes:
t71: randomly taking values based on the M stamping control trigger intervals to obtain stamping control and sound fields, wherein the stamping control and sound fields comprise a plurality of stamping control and sound, and each stamping control and sound comprises M stamping control index values corresponding to M stamping control indexes;
t72: randomly selecting based on the punching control and the sound domain to obtain a first punching control sound;
t73: according to the punching control harmony optimizing function and the first punching processing characteristic information, carrying out adaptation and acoustic evaluation on the first punching control harmony to obtain first control harmony adaptation degree;
t74: continuously randomly selecting the punching control and the sound domain to obtain a second punching control harmony, and carrying out adaptation and sound evaluation on the second punching control harmony according to the punching control harmony optimizing function and the first punching processing characteristic information to obtain a second control harmony fitness;
t75: judging whether the first control harmony adaptability is larger than the second control harmony adaptability;
t76: if the first control harmony measures are larger than the second control harmony measures, the first punching control harmony measures are taken as the current optimal punching control harmony measures, and the second punching control harmony measures are eliminated;
T77: if the first control harmony measures are smaller than/equal to the second control harmony measures, taking the second punching control harmony measures as the current optimal punching control harmony measures, and eliminating the first punching control harmony measures;
t78: and carrying out iterative optimization according to the stamping control and the sound field based on the current optimal stamping control harmony, obtaining iterative optimal stamping control harmony when the optimizing times meet the optimizing times constraint in the binary optimizing constraint, and generating the first optimal stamping control decision according to the iterative optimal stamping control harmony.
Specifically, random values are taken from the M stamping control trigger intervals, stamping control and sound fields are obtained, the stamping control and sound fields comprise a plurality of stamping control and sound, each stamping control and sound field comprises M stamping control index values corresponding to M stamping control indexes, namely stamping control parameter sets, and the stamping control and sound fields are stamping control parameter values, and the stamping control and sound field comprises a plurality of stamping control parameter values such as die temperature, stamping force, stamping speed and the like.
Further, a first punching control and sound, that is, a first set of punching control parameter values, are obtained by randomly selecting the punching control and sound domain, and the first punching processing characteristic information is substituted into the punching control and sound optimizing function for the first punching control and sound, so as to calculate the fitness and obtain the first control and sound fitness. And similarly, continuing to randomly select from the punching control and the sound domain to obtain second punching control harmony, substituting the second punching control harmony into the punching control harmony optimizing function to perform adaptation harmony evaluation, and calculating to obtain second control harmony fitness.
Further, comparing and judging whether the first control harmony adaptability is larger than the second control harmony adaptability, if so, taking the first punching control harmony as the current optimal punching control harmony, namely, as a temporary optimal solution, and eliminating the second punching control harmony, and if not, taking the second punching control harmony as the current optimal punching control harmony, and eliminating the first punching control harmony. And by analogy, based on the current optimal stamping control harmony, iterative optimization is carried out in the stamping control harmony domain, when the optimizing times meet the optimizing times constraint in the binary optimizing constraint, the stamping control harmony obtained in the last iteration is used as the iterative optimal stamping control harmony, the first optimal stamping control decision is generated according to the iterative optimal stamping control harmony, and the first optimal stamping control decision is used for stamping, so that the control precision and accuracy of stator and rotor stamping parameters can be improved, and the quality of a stamped product is further improved.
Further, step T73 in the embodiment of the present application further includes:
t73-1: collecting punching sheet processing result records in a preset historical time zone based on the first punching control harmony to obtain a first sum sound processing result record set;
T73-2: calibrating trigger records of the first and sound processing result record sets based on the first punching processing characteristic information to obtain a plurality of first and sound trigger records;
t73-3: generating the first control and acoustic fitness based on the stamping control and acoustic optimization function according to the first and acoustic machining result record set and the plurality of first and acoustic trigger records, wherein the stamping control and acoustic optimization function is as follows:
；
wherein,characterizing j-th control and harmony fitness, +.>For a total number of j-th and acoustic trigger recordings,the total number of records in the j-th and sound processing result record sets.
The method comprises the steps of referring to first punching control and sound, namely a first group of punching control parameters, collecting punching processing result records in a preset historical time zone, wherein the preset historical time zone can be three months, half years and the like in the past, specific time can be adaptively adjusted according to actual conditions, a first and sound processing result record set is obtained, namely a finished product quality record of a finished product obtained after punching by using the first group of punching control parameters, comprising size, appearance and the like, is compared with various product requirements in first punching processing characteristic information, indexes meeting requirements, such as appearance standard, inner diameter size standard and the like, are screened out, and are used as product requirement triggering indexes, triggering record calibration is carried out, so that a plurality of first and sound triggering records are obtained, and the standard condition of the product requirements can be reflected.
Further, substituting the first and acoustic processing result record set and the plurality of first and acoustic trigger records into the punching control and acoustic optimizing function to calculate, and generating the first control and acoustic fitness, wherein the punching control and acoustic optimizing function is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Characterizing jth control and harmony adaptationDegree (f)>Total number of sound trigger recordings for a plurality of j-th and +.>The total number of records in the j-th and sound processing result record sets.
Further, as shown in fig. 3, step T78 in the embodiment of the present application further includes:
t78-1: obtaining the iterative optimal control and acoustic fitness corresponding to the iterative optimal stamping control and acoustic;
t78-2: judging whether the iterative optimal control and acoustic fitness meet the control and acoustic fitness constraint in the binary optimizing constraint;
t78-3: if the iterative optimal control and acoustic fitness meets the control and acoustic fitness constraints, outputting the iterative optimal stamping control and acoustic as the first optimal stamping control decision;
t78-4: and if the iterative optimal control and harmony adaptability does not meet the control and harmony adaptability constraint, randomly adjusting the iterative optimal stamping control and harmony to obtain stamping control compensation and a sound domain meeting the M stamping control trigger intervals, and performing iterative optimization on the stamping control compensation and the sound domain until the first optimal stamping control decision is output.
In one possible embodiment of the present application, after the first iteration optimizing is finished, the iteration optimal stamping control and acoustic fitness corresponding to the iteration optimal stamping control and acoustic fitness is extracted and compared with the control and acoustic fitness constraint in the binary optimizing constraint, the control and acoustic fitness constraint is set according to the production precision requirement, for example, set to 80%, whether the iteration optimal stamping control and acoustic fitness meets the control and acoustic fitness constraint in the binary optimizing constraint is judged, and if yes, the iteration optimal stamping control and acoustic output is the first optimal stamping control decision.
If the first and second optimal stamping control harmony values do not meet the requirement, secondary optimization is needed, namely the iterative optimal stamping control harmony values are randomly adjusted, stamping control compensation and a sound domain are reselected from the M stamping control trigger intervals, and the stamping control compensation and the sound domain are used for secondary iterative optimization until the iterative optimal stamping control harmony values with the fitness meeting the control and sound fitness constraint are obtained, and are output as the first optimal stamping control decision.
In summary, the embodiments of the present application have at least the following technical effects:
According to the method, the motor stator and rotor machining requirements are subjected to punching machining feature analysis, a punching machining feature analysis set is generated, a punching machining control set is collected, then the punching machining control set is clustered based on M punching control indexes, M punching control subsets are obtained, M punching control triggering intervals are calibrated, optimization is performed by combining punching control and an acoustic optimizing function, and a first optimal punching control decision is obtained to execute punching control.
The technical effect of improving the quality of stator and rotor punching sheets by improving the control precision and accuracy of punching parameters is achieved.
Example two
Based on the same inventive concept as the stamping control method for processing the stator and the rotor of the motor in the foregoing embodiments, as shown in fig. 4, the present application provides a stamping control system for processing the stator and the rotor of the motor, and the system and the method embodiments in the embodiments of the present application are based on the same inventive concept. Wherein the system comprises:
the stator and rotor machining requirement acquisition module 11 is used for acquiring the machining requirement of the stator and rotor of the motor;
the punching processing analysis index obtaining module 12 is used for obtaining a ternary punching processing analysis index, wherein the ternary punching processing analysis index comprises a punching processing number index, a punching processing material index and a punching processing structure index;
The punching processing characteristic analysis module 13 is used for carrying out punching processing characteristic analysis on the motor stator and rotor processing requirements according to the ternary punching processing analysis index to generate a punching processing characteristic analysis set;
a preset press control index set obtaining module 14, where the preset press control index set obtaining module 14 is configured to obtain a preset press control index set, and the preset press control index set includes M press control indexes, where M is a positive integer greater than 1;
the punching processing control set acquisition module 15 is used for acquiring first punching processing characteristic information based on the punching processing characteristic analysis set, and performing data mining according to the first punching processing characteristic information and the preset punching control index set to acquire a punching processing control set;
the punching control trigger interval obtaining module 16, where the punching control trigger interval obtaining module 16 is configured to cluster the punching processing control set based on the M punching control indexes to obtain M punching control subsets, and execute trigger interval calibration of the M punching control indexes according to the M punching control subsets to obtain M punching control trigger intervals corresponding to the M punching control indexes;
The punching control module 17 is configured to optimize the M punching control trigger intervals according to a pre-constructed punching control and sound optimizing function and a binary optimizing constraint based on the first punching processing feature information, obtain a first optimal punching control decision, and execute punching control of the first punching processing feature information according to the first optimal punching control decision.
Further, the punching processing characteristic analysis module 13 is further configured to perform the following steps:
obtaining a sample punching processing characteristic analysis library, wherein the sample punching processing characteristic analysis library comprises a sample stator and rotor processing requirement record, a sample punching processing number record, a sample punching processing material record and a sample punching processing structure record;
based on a pre-constructed confidence accurate analysis function, constructing a punching processing number analysis layer corresponding to the punching processing number index according to the sample stator and rotor processing requirement record and the sample punching processing number record;
based on the confidence accurate analysis function, constructing a punching processing material analysis layer corresponding to the punching processing material index according to the sample stator and rotor processing requirement record and the sample punching processing material record;
Based on the confidence accurate analysis function, constructing a punching processing structure analysis layer corresponding to the punching processing structure index according to the sample stator and rotor processing demand record and the sample punching processing structure record;
integrating the punching processing number analysis layer, the punching processing material analysis layer and the punching processing structure analysis layer to generate a punching processing characteristic analyzer;
and executing the punching processing characteristic analysis of the motor stator and rotor processing requirements according to the punching processing characteristic analyzer to obtain the punching processing characteristic analysis set.
Further, the punching processing characteristic analysis module 13 is further configured to perform the following steps:
constructing the confidence accurate analysis function, wherein the confidence accurate analysis function is as follows:
；
wherein,characterization test confidence coefficient of accuracy,/->Characterization of test accuracy,/->The test error loss rate is characterized.
Further, the punching processing characteristic analysis module 13 is further configured to perform the following steps:
the processing requirement record of the sample stator and the rotor and the processing quantity record of the sample punching sheet are used as a first construction data sequence, and the first construction data sequence is randomly divided according to a preset division operator to obtain a first training data sequence and a first test data sequence;
Performing supervised training on the fully-connected neural network according to the first training data sequence to obtain a first punching processing number analyzer;
testing the first punching processing number analyzer according to the first test data sequence to obtain a first test accuracy rate and a first test error loss rate;
inputting the first test accuracy rate and the first test error loss rate into the confidence accuracy analysis function to obtain a first test confidence accuracy coefficient;
judging whether the first test confidence accuracy coefficient meets a preset confidence accuracy interval or not;
if the first test confidence accuracy coefficient meets the preset confidence accuracy interval, embedding the first punching processing number analyzer into the punching processing number analysis layer;
if the first test confidence accuracy coefficient does not meet the preset confidence accuracy interval, a first loss data sequence is obtained, incremental learning is conducted on the first punching processing number analyzer according to the first loss data sequence until a second punching processing number analyzer meeting the preset confidence accuracy interval is generated, and the second punching processing number analyzer is embedded into the punching processing number analysis layer.
Further, the stamping control module 17 is further configured to perform the following steps:
randomly taking values based on the M stamping control trigger intervals to obtain stamping control and sound fields, wherein the stamping control and sound fields comprise a plurality of stamping control and sound, and each stamping control and sound comprises M stamping control index values corresponding to M stamping control indexes;
randomly selecting based on the punching control and the sound domain to obtain a first punching control sound;
according to the punching control harmony optimizing function and the first punching processing characteristic information, carrying out adaptation and acoustic evaluation on the first punching control harmony to obtain first control harmony adaptation degree;
continuously randomly selecting the punching control and the sound domain to obtain a second punching control harmony, and carrying out adaptation and sound evaluation on the second punching control harmony according to the punching control harmony optimizing function and the first punching processing characteristic information to obtain a second control harmony fitness;
judging whether the first control harmony adaptability is larger than the second control harmony adaptability;
if the first control harmony measures are larger than the second control harmony measures, the first punching control harmony measures are taken as the current optimal punching control harmony measures, and the second punching control harmony measures are eliminated;
If the first control harmony measures are smaller than/equal to the second control harmony measures, taking the second punching control harmony measures as the current optimal punching control harmony measures, and eliminating the first punching control harmony measures;
and carrying out iterative optimization according to the stamping control and the sound field based on the current optimal stamping control harmony, obtaining iterative optimal stamping control harmony when the optimizing times meet the optimizing times constraint in the binary optimizing constraint, and generating the first optimal stamping control decision according to the iterative optimal stamping control harmony.
Further, the stamping control module 17 is further configured to perform the following steps:
collecting punching sheet processing result records in a preset historical time zone based on the first punching control harmony to obtain a first sum sound processing result record set;
calibrating trigger records of the first and sound processing result record sets based on the first punching processing characteristic information to obtain a plurality of first and sound trigger records;
generating the first control and acoustic fitness based on the stamping control and acoustic optimization function according to the first and acoustic machining result record set and the plurality of first and acoustic trigger records, wherein the stamping control and acoustic optimization function is as follows:
；
Wherein,characterizing j-th control and harmony fitness, +.>For a total number of j-th and acoustic trigger recordings,the total number of records in the j-th and sound processing result record sets.
Further, the stamping control module 17 is further configured to perform the following steps:
obtaining the iterative optimal control and acoustic fitness corresponding to the iterative optimal stamping control and acoustic;
judging whether the iterative optimal control and acoustic fitness meet the control and acoustic fitness constraint in the binary optimizing constraint;
if the iterative optimal control and acoustic fitness meets the control and acoustic fitness constraints, outputting the iterative optimal stamping control and acoustic as the first optimal stamping control decision;
and if the iterative optimal control and harmony adaptability does not meet the control and harmony adaptability constraint, randomly adjusting the iterative optimal stamping control and harmony to obtain stamping control compensation and a sound domain meeting the M stamping control trigger intervals, and performing iterative optimization on the stamping control compensation and the sound domain until the first optimal stamping control decision is output.
It should be noted that the sequence of the embodiments of the present application is merely for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the present application is not intended to limit the invention to the particular embodiments of the present application, but to limit the scope of the invention to the particular embodiments of the present application.
The specification and drawings are merely exemplary of the application and are to be regarded as covering any and all modifications, variations, combinations, or equivalents that are within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (5)
1. The stamping control method for the processing of the stator and the rotor of the motor is characterized by comprising the following steps:
obtaining the processing requirement of a stator and a rotor of a motor;
obtaining a ternary punching processing analysis index, wherein the ternary punching processing analysis index comprises a punching processing number index, a punching processing material index and a punching processing structure index;
performing punching processing characteristic analysis on the motor stator and rotor processing requirements according to the ternary punching processing analysis index to generate a punching processing characteristic analysis set;
Obtaining a preset punching control index set, wherein the preset punching control index set comprises M punching control indexes, and M is a positive integer greater than 1;
based on the punching processing characteristic analysis set, first punching processing characteristic information is obtained, and data mining is carried out according to the first punching processing characteristic information and the preset punching control index set, so that a punching processing control set is obtained;
clustering the punching processing control sets based on the M punching control indexes to obtain M punching control subsets, and executing triggering interval calibration of the M punching control indexes according to the M punching control subsets to obtain M punching control triggering intervals corresponding to the M punching control indexes;
optimizing the M stamping control trigger intervals according to a pre-constructed stamping control and sound optimizing function and binary optimizing constraint based on the first stamping processing characteristic information to obtain a first optimal stamping control decision, and executing stamping control of the first stamping processing characteristic information according to the first optimal stamping control decision;
based on the first punching processing characteristic information, optimizing the M punching control trigger intervals according to a pre-constructed punching control and sound optimizing function and binary optimizing constraint to obtain a first optimal punching control decision, wherein the method comprises the following steps:
Randomly taking values based on the M stamping control trigger intervals to obtain stamping control and sound fields, wherein the stamping control and sound fields comprise a plurality of stamping control and sound, and each stamping control and sound comprises M stamping control index values corresponding to M stamping control indexes;
randomly selecting based on the punching control and the sound domain to obtain a first punching control sound;
according to the punching control harmony optimizing function and the first punching processing characteristic information, carrying out adaptation and acoustic evaluation on the first punching control harmony to obtain first control harmony adaptation degree;
continuously randomly selecting the punching control and the sound domain to obtain a second punching control harmony, and carrying out adaptation and sound evaluation on the second punching control harmony according to the punching control harmony optimizing function and the first punching processing characteristic information to obtain a second control harmony fitness;
judging whether the first control harmony adaptability is larger than the second control harmony adaptability;
if the first control harmony measures are larger than the second control harmony measures, the first punching control harmony measures are taken as the current optimal punching control harmony measures, and the second punching control harmony measures are eliminated;
If the first control harmony measures are smaller than/equal to the second control harmony measures, taking the second punching control harmony measures as the current optimal punching control harmony measures, and eliminating the first punching control harmony measures;
performing iterative optimization according to the stamping control and the sound domain based on the current optimal stamping control harmony, obtaining iterative optimal stamping control harmony when the optimizing times meet optimizing times constraint in the binary optimizing constraint, and generating the first optimal stamping control decision according to the iterative optimal stamping control harmony;
and performing adaptation and acoustic evaluation on the first punching control and sound according to the punching control and sound optimizing function and the first punching processing characteristic information to obtain first control and sound adaptation degree, wherein the method comprises the following steps:
collecting punching sheet processing result records in a preset historical time zone based on the first punching control harmony to obtain a first sum sound processing result record set;
calibrating trigger records of the first and sound processing result record sets based on the first punching processing characteristic information to obtain a plurality of first and sound trigger records;
generating the first control and acoustic fitness based on the stamping control and acoustic optimization function according to the first and acoustic machining result record set and the plurality of first and acoustic trigger records, wherein the stamping control and acoustic optimization function is as follows:
；
Wherein,characterizing j-th control and harmony fitness, +.>Total number of sound trigger recordings for a plurality of j-th and +.>The total number of records in the j-th and sound processing result record sets.
2. The method of claim 1, wherein performing a lamination process feature analysis on the motor stator and rotor process requirements according to the ternary lamination process analysis index to generate a lamination process feature analysis set, comprising:
obtaining a sample punching processing characteristic analysis library, wherein the sample punching processing characteristic analysis library comprises a sample stator and rotor processing requirement record, a sample punching processing number record, a sample punching processing material record and a sample punching processing structure record;
based on a pre-constructed confidence accurate analysis function, constructing a punching processing number analysis layer corresponding to the punching processing number index according to the sample stator and rotor processing requirement record and the sample punching processing number record, wherein the confidence accurate analysis function is constructed, and the confidence accurate analysis function is as follows:
；
wherein,characterization test confidence coefficient of accuracy,/->Characterization of test accuracy,/->Characterizing a test error loss rate;
based on the confidence accurate analysis function, constructing a punching processing material analysis layer corresponding to the punching processing material index according to the sample stator and rotor processing requirement record and the sample punching processing material record;
Based on the confidence accurate analysis function, constructing a punching processing structure analysis layer corresponding to the punching processing structure index according to the sample stator and rotor processing demand record and the sample punching processing structure record;
integrating the punching processing number analysis layer, the punching processing material analysis layer and the punching processing structure analysis layer to generate a punching processing characteristic analyzer;
and executing the punching processing characteristic analysis of the motor stator and rotor processing requirements according to the punching processing characteristic analyzer to obtain the punching processing characteristic analysis set.
3. The method of claim 2, wherein constructing a die process number resolution layer corresponding to the die process number index comprises:
the processing requirement record of the sample stator and the rotor and the processing quantity record of the sample punching sheet are used as a first construction data sequence, and the first construction data sequence is randomly divided according to a preset division operator to obtain a first training data sequence and a first test data sequence;
performing supervised training on the fully-connected neural network according to the first training data sequence to obtain a first punching processing number analyzer;
testing the first punching processing number analyzer according to the first test data sequence to obtain a first test accuracy rate and a first test error loss rate;
Inputting the first test accuracy rate and the first test error loss rate into the confidence accuracy analysis function to obtain a first test confidence accuracy coefficient;
judging whether the first test confidence accuracy coefficient meets a preset confidence accuracy interval or not;
if the first test confidence accuracy coefficient meets the preset confidence accuracy interval, embedding the first punching processing number analyzer into the punching processing number analysis layer;
if the first test confidence accuracy coefficient does not meet the preset confidence accuracy interval, a first loss data sequence is obtained, incremental learning is conducted on the first punching processing number analyzer according to the first loss data sequence until a second punching processing number analyzer meeting the preset confidence accuracy interval is generated, and the second punching processing number analyzer is embedded into the punching processing number analysis layer.
4. The method of claim 1, wherein generating the first optimal press control decision from the iterative optimal press control harmony comprises:
obtaining the iterative optimal control and acoustic fitness corresponding to the iterative optimal stamping control and acoustic;
Judging whether the iterative optimal control and acoustic fitness meet the control and acoustic fitness constraint in the binary optimizing constraint;
if the iterative optimal control and acoustic fitness meets the control and acoustic fitness constraints, outputting the iterative optimal stamping control and acoustic as the first optimal stamping control decision;
and if the iterative optimal control and harmony adaptability does not meet the control and harmony adaptability constraint, randomly adjusting the iterative optimal stamping control and harmony to obtain stamping control compensation and a sound domain meeting the M stamping control trigger intervals, and performing iterative optimization on the stamping control compensation and the sound domain until the first optimal stamping control decision is output.
5. A stamping control system for motor stator and rotor machining, the system comprising:
the stator and rotor machining requirement acquisition module is used for acquiring the machining requirement of the stator and rotor of the motor;
the punching processing analysis index obtaining module is used for obtaining ternary punching processing analysis indexes, wherein the ternary punching processing analysis indexes comprise punching processing number indexes, punching processing material indexes and punching processing structure indexes;
The punching processing characteristic analysis module is used for carrying out punching processing characteristic analysis on the motor stator and rotor processing requirements according to the ternary punching processing analysis index to generate a punching processing characteristic analysis set;
the device comprises a preset punching control index set obtaining module, a punching control index set processing module and a punching control index set processing module, wherein the preset punching control index set obtaining module is used for obtaining a preset punching control index set, the preset punching control index set comprises M punching control indexes, and M is a positive integer larger than 1;
the punching processing control set acquisition module is used for acquiring first punching processing characteristic information based on the punching processing characteristic analysis set, and carrying out data mining according to the first punching processing characteristic information and the preset punching control index set to acquire a punching processing control set;
the punching control trigger interval obtaining module is used for clustering the punching processing control sets based on the M punching control indexes to obtain M punching control subsets, and executing trigger interval calibration of the M punching control indexes according to the M punching control subsets to obtain M punching control trigger intervals corresponding to the M punching control indexes;
The punching control module is used for optimizing the M punching control trigger intervals according to a pre-constructed punching control and sound optimizing function and binary optimizing constraint based on the first punching processing characteristic information to obtain a first optimal punching control decision, and executing punching control of the first punching processing characteristic information according to the first optimal punching control decision;
the stamping control module is also used for executing the following steps:
randomly taking values based on the M stamping control trigger intervals to obtain stamping control and sound fields, wherein the stamping control and sound fields comprise a plurality of stamping control and sound, and each stamping control and sound comprises M stamping control index values corresponding to M stamping control indexes;
randomly selecting based on the punching control and the sound domain to obtain a first punching control sound;
according to the punching control harmony optimizing function and the first punching processing characteristic information, carrying out adaptation and acoustic evaluation on the first punching control harmony to obtain first control harmony adaptation degree;
continuously randomly selecting the punching control and the sound domain to obtain a second punching control harmony, and carrying out adaptation and sound evaluation on the second punching control harmony according to the punching control harmony optimizing function and the first punching processing characteristic information to obtain a second control harmony fitness;
Judging whether the first control harmony adaptability is larger than the second control harmony adaptability;
if the first control harmony measures are larger than the second control harmony measures, the first punching control harmony measures are taken as the current optimal punching control harmony measures, and the second punching control harmony measures are eliminated;
if the first control harmony measures are smaller than/equal to the second control harmony measures, taking the second punching control harmony measures as the current optimal punching control harmony measures, and eliminating the first punching control harmony measures;
performing iterative optimization according to the stamping control and the sound domain based on the current optimal stamping control harmony, obtaining iterative optimal stamping control harmony when the optimizing times meet optimizing times constraint in the binary optimizing constraint, and generating the first optimal stamping control decision according to the iterative optimal stamping control harmony; collecting punching sheet processing result records in a preset historical time zone based on the first punching control harmony to obtain a first sum sound processing result record set;
calibrating trigger records of the first and sound processing result record sets based on the first punching processing characteristic information to obtain a plurality of first and sound trigger records;
Generating the first control and acoustic fitness based on the stamping control and acoustic optimization function according to the first and acoustic machining result record set and the plurality of first and acoustic trigger records, wherein the stamping control and acoustic optimization function is as follows:
；
wherein,characterizing j-th control and harmony fitness, +.>Total number of sound trigger recordings for a plurality of j-th and +.>The total number of records in the j-th and sound processing result record sets.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311350642.XA CN117066337B (en) | 2023-10-18 | 2023-10-18 | Stamping control method and system for motor stator and rotor machining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311350642.XA CN117066337B (en) | 2023-10-18 | 2023-10-18 | Stamping control method and system for motor stator and rotor machining |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117066337A CN117066337A (en) | 2023-11-17 |
| CN117066337B true CN117066337B (en) | 2023-12-29 |
Family
ID=88708469
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311350642.XA Active CN117066337B (en) | 2023-10-18 | 2023-10-18 | Stamping control method and system for motor stator and rotor machining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117066337B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112718921A (en) * | 2020-12-29 | 2021-04-30 | 南通双耀冲压有限公司 | Quality detection method and device for motor rotor stamping die |
| CN115720031A (en) * | 2022-10-24 | 2023-02-28 | 江阴市鑫志冲件有限公司 | Motor stator and rotor punching slotting depth deviation identification system |
| CN116213962A (en) * | 2023-05-10 | 2023-06-06 | 杭州乾瑭云科技有限公司 | Metal plate cutting control method and system based on state prediction |
| CN116541980A (en) * | 2023-04-26 | 2023-08-04 | 博格华纳汽车零部件（武汉）有限公司 | Rotor punching size parameter optimization method |
| CN116679658A (en) * | 2023-08-03 | 2023-09-01 | 江苏甬金金属科技有限公司 | Optimized production control method and system for stainless steel band |
| CN116776620A (en) * | 2023-06-30 | 2023-09-19 | 大捷智能科技(广东)有限公司 | Stamping process data analysis method and system |
| CN116846162A (en) * | 2023-07-14 | 2023-10-03 | 中海石油(中国)有限公司深圳分公司 | Method and device for controlling stator lamination of submersible motor, electronic equipment and storage medium |
-
2023
- 2023-10-18 CN CN202311350642.XA patent/CN117066337B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112718921A (en) * | 2020-12-29 | 2021-04-30 | 南通双耀冲压有限公司 | Quality detection method and device for motor rotor stamping die |
| CN115720031A (en) * | 2022-10-24 | 2023-02-28 | 江阴市鑫志冲件有限公司 | Motor stator and rotor punching slotting depth deviation identification system |
| CN116541980A (en) * | 2023-04-26 | 2023-08-04 | 博格华纳汽车零部件（武汉）有限公司 | Rotor punching size parameter optimization method |
| CN116213962A (en) * | 2023-05-10 | 2023-06-06 | 杭州乾瑭云科技有限公司 | Metal plate cutting control method and system based on state prediction |
| CN116776620A (en) * | 2023-06-30 | 2023-09-19 | 大捷智能科技(广东)有限公司 | Stamping process data analysis method and system |
| CN116846162A (en) * | 2023-07-14 | 2023-10-03 | 中海石油(中国)有限公司深圳分公司 | Method and device for controlling stator lamination of submersible motor, electronic equipment and storage medium |
| CN116679658A (en) * | 2023-08-03 | 2023-09-01 | 江苏甬金金属科技有限公司 | Optimized production control method and system for stainless steel band |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117066337A (en) | 2023-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109514349B (en) | Tool wear state monitoring method based on vibration signal and Stacking integrated model | |
| US20080154816A1 (en) | Artificial neural network with adaptable infinite-logic nodes | |
| CN110068544B (en) | Substance identification network model training method and terahertz spectrum substance identification method | |
| CN112294341B (en) | Sleep electroencephalogram spindle wave identification method and system based on light convolutional neural network | |
| CN111898443B (en) | Flow monitoring method for wire feeding mechanism of FDM type 3D printer | |
| CN109459235B (en) | Enhanced gear single fault category diagnosis method based on integrated learning | |
| CN106874943A (en) | Business object sorting technique and system | |
| CN112541510A (en) | Intelligent fault diagnosis method based on multi-channel time series data | |
| CN116520772A (en) | Sheet part numerical control machining quality prediction method based on multitasking transfer learning | |
| CN109254577A (en) | A kind of intelligence manufacture procedure fault classification method and device based on deep learning | |
| CN112528955A (en) | High-frequency element machining size precision prediction method and system | |
| CN115221973A (en) | Aviation bearing fault diagnosis method based on enhanced weighted heterogeneous ensemble learning | |
| CN114912720A (en) | Memory network-based power load prediction method, device, terminal and storage medium | |
| CN117066337B (en) | Stamping control method and system for motor stator and rotor machining | |
| CN113642255A (en) | Photovoltaic power generation power prediction method based on multi-scale convolution cyclic neural network | |
| CN113516173A (en) | Evaluation method for static and dynamic interference of whole vehicle based on random forest and decision tree | |
| CN110320802B (en) | Complex system signal time sequence identification method based on data visualization | |
| CN116776245A (en) | Three-phase inverter equipment fault diagnosis method based on machine learning | |
| US20020059151A1 (en) | Data analysis | |
| CN109493249B (en) | Analysis method of electricity consumption data on multiple time scales | |
| CN109782167A (en) | Toothed gearing electric motor product examine device and method based on convolutional network depth model | |
| CN114021275A (en) | Rolling bearing fault diagnosis method based on deep convolution fuzzy system | |
| CN109359694B (en) | Image classification method and device based on mixed collaborative representation classifier | |
| Corchado et al. | Optimizing the operating conditions in a high precision industrial process using soft computing techniques | |
| Qin | A cancer cell image classification program: based on CNN model |
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 |