CN116681266A - Production scheduling method and system of mirror surface electric discharge machine - Google Patents
Production scheduling method and system of mirror surface electric discharge machine Download PDFInfo
- Publication number
- CN116681266A CN116681266A CN202310959932.8A CN202310959932A CN116681266A CN 116681266 A CN116681266 A CN 116681266A CN 202310959932 A CN202310959932 A CN 202310959932A CN 116681266 A CN116681266 A CN 116681266A
- Authority
- CN
- China
- Prior art keywords
- electric discharge
- discharge machine
- machining precision
- mirror surface
- surface electric
- 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.)
- Granted
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 90
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000012545 processing Methods 0.000 claims abstract description 97
- 238000009826 distribution Methods 0.000 claims abstract description 10
- 238000003754 machining Methods 0.000 claims description 315
- 239000011159 matrix material Substances 0.000 claims description 54
- 230000002159 abnormal effect Effects 0.000 claims description 49
- 238000011156 evaluation Methods 0.000 claims description 36
- 238000012937 correction Methods 0.000 claims description 13
- 238000000354 decomposition reaction Methods 0.000 claims description 13
- 238000010586 diagram Methods 0.000 claims description 10
- 230000000007 visual effect Effects 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 8
- 230000002068 genetic effect Effects 0.000 claims description 7
- 210000000349 chromosome Anatomy 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000011176 pooling Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 abstract description 7
- 230000008859 change Effects 0.000 abstract description 3
- 238000003860 storage Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 6
- 238000010892 electric spark Methods 0.000 description 4
- 238000010219 correlation analysis Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005459 micromachining Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2337—Non-hierarchical techniques using fuzzy logic, i.e. fuzzy clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- 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
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Fuzzy Systems (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Automation & Control Theory (AREA)
- Manufacturing & Machinery (AREA)
- Primary Health Care (AREA)
- Electrical Discharge Machining, Electrochemical Machining, And Combined Machining (AREA)
Abstract
The invention relates to a production scheduling method AND a system of a mirror surface electric discharge machine, which belong to the technical field of production scheduling. The invention improves the fuzzy clustering algorithm by introducing the AND algorithm, AND can improve the clustering precision, thereby improving the distribution precision of the mirror surface electric discharge machine in the production scheduling process; and secondly, the invention fully considers the processing precision change of the mirror surface electric discharge machine, thereby optimizing the production schedule according to the processing precision data and improving the rationality of the production schedule.
Description
Technical Field
The invention relates to the technical field of production scheduling, in particular to a production scheduling method and system of a mirror surface electric discharge machine.
Background
The mirror surface electric discharge machine is one of electric discharge machining devices, and the electric discharge machining technology has been widely used in the fields of aviation, aerospace, dies, cutters, precision instruments, micromachining and the like, and particularly in the field of die manufacturing. In the process of manufacturing the die, the specific gravity of the electric spark processing technology is far higher than that of other processing methods, and the electric spark processing technology has an irreplaceable function. Data show that 30% -50% of machining quantity in the die industry is directly finished by an electric spark machining machine tool; in the electric spark machining equipment produced in the machine tool industry, 80% of the equipment is directly used for die machining. Shop floor scheduling problem is one of the most fundamental problems in the study of manufacturing systems, as well as the emphasis and difficulty ‚. Shop floor scheduling generally involves a relatively large number of factors ‚ and thus a relatively large difficulty ‚, particularly the presence of many unknown uncertainty factors ‚ in the operating environment itself of modern manufacturing systems, makes the shop floor scheduling problem more and more difficult. The research on workshop production scheduling problem has become a key technology for improving workshop production efficiency and improving enterprise competitiveness. The effective scheduling method and the optimization technology are the basis and key of workshop production scheduling problems. In the current problem of production scheduling of the mirror surface electric discharge machine, as the mirror surface electric discharge machine causes the reduction of machining precision in the repeated use process, when the machining precision is reduced, the machining requirement of machined parts is not necessarily met, thereby causing the production scheduling to be not reasonable and causing a large number of machining defective products.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a production scheduling method and a system of a mirror surface electric discharge machine.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the first aspect of the present invention provides a production scheduling method of a mirror surface electric discharge machine, comprising the steps of:
acquiring machining precision state information of each mirror surface electric discharge machine of a current enterprise, and predicting machining precision state information within the next preset time according to the machining precision state information of the mirror surface electric discharge machine;
introducing a fuzzy clustering algorithm, and performing fuzzy clustering on the mirror surface electric discharge machining machines according to machining precision state information within the next preset time through the fuzzy clustering algorithm to generate a final clustering center and machining precision membership of each mirror surface electric discharge machining machine;
introducing an AND algorithm, AND correcting the machining precision membership of the mirror surface electric discharge machine through the AND algorithm to obtain the machining precision membership of the corrected mirror surface electric discharge machine;
and acquiring production order information of the mirror surface electric discharge machine, and generating a production scheduling result according to the machining precision membership degree of the corrected mirror surface electric discharge machine and the production order information of the mirror surface electric discharge machine.
Further, in a preferred embodiment of the present invention, the obtaining the machining precision state information of each mirror surface electric discharge machine of the current enterprise, and estimating the machining precision state information within the next preset time according to the machining precision state information of the mirror surface electric discharge machine specifically includes:
acquiring machining precision state information of each mirror surface electric discharge machine of a current enterprise, constructing a time stamp, combining the time stamp and the machining precision state information of each mirror surface electric discharge machine of the current enterprise to construct machining precision state information of each mirror surface electric discharge machine based on a time sequence, and storing the machining precision state information in a database;
acquiring machining precision state information of each mirror surface electric discharge machine based on a time sequence through the database, constructing a machining precision state prediction model based on a convolutional neural network, and constructing a feature matrix according to the machining precision state information of each mirror surface electric discharge machine based on the time sequence;
introducing a singular value decomposition algorithm into a convolution layer, processing the feature matrix through the singular value decomposition algorithm to generate a covariance matrix, inputting the covariance matrix into a pooling layer and a full-connection layer, identifying through an output vector, classifying through Softmax, storing model parameters, and outputting a processing precision state prediction model;
The method comprises the steps of obtaining machining precision state information of each mirror surface electric discharge machine within preset time, inputting the machining precision state information of each mirror surface electric discharge machine within the preset time into the machining precision state prediction model, and obtaining machining precision state information within the next preset time.
Further, in a preferred embodiment of the present invention, the introducing a fuzzy clustering algorithm, and performing fuzzy clustering on the mirror surface electric discharge machine according to the machining precision state information within the next preset time by using the fuzzy clustering algorithm, to generate a final clustering center and a machining precision membership degree of each mirror surface electric discharge machine, specifically includes:
constructing a machining precision sample data set of the mirror surface electric discharge machine based on the machining precision state information within the next preset time, introducing a fuzzy clustering algorithm, initializing the range of a clustering center, introducing a genetic algorithm, and setting the number of chromosomes, the maximum iteration factor and the learning factor;
setting the clustering number, iteration termination condition, maximum iteration times, gaussian kernel number, gaussian kernel parameters and constraint coefficients according to a processing precision sample data set of the mirror surface electric discharge machine, and continuously updating a clustering center and a membership matrix through an objective function of the fuzzy clustering algorithm;
Stopping iteration when the maximum iteration times are reached, acquiring a corresponding membership matrix, acquiring a clustering center in the corresponding membership matrix, and taking the clustering center in the corresponding membership matrix as an optimal clustering center;
and generating a final clustering center and machining precision membership degrees of each mirror surface electric discharge machine according to the corresponding membership degree matrix and the optimal clustering center.
Further, in a preferred embodiment of the present invention, the introducing an AND algorithm corrects the machining precision membership of the mirror electric discharge machine by the AND algorithm to obtain the corrected machining precision membership of the mirror electric discharge machine, AND specifically includes:
introducing an AND algorithm, acquiring position nodes of each sample data in a machining precision sample data set of the mirror surface electric discharge machine, AND presetting a plurality of similarity indexes;
calculating a node evolution vector of a position node of each sample data in a processing precision sample data set of the mirror surface electric discharge machine under different similarity indexes;
performing abnormal evolution judgment on the node evolution vector through vector cosine similarity, obtaining an abnormal evolution node, constructing an abnormal evolution set, and inputting the abnormal evolution node into the abnormal evolution set;
Sample data corresponding to the abnormal evolution nodes in the abnormal evolution set are obtained, the sample data are redistributed to the class clusters corresponding to other clustering centers until the abnormal evolution nodes are not generated, and the machining precision membership of the mirror surface electric discharge machine after correction is generated.
Further, in a preferred embodiment of the present invention, the obtaining production order information of the mirror electric discharge machine, and generating a production scheduling result according to the machining precision membership of the mirror electric discharge machine after correction and the production order information of the mirror electric discharge machine specifically includes:
acquiring production order information of a mirror surface electric discharge machine, acquiring machining precision data information of each machined part according to the production order information of the mirror surface electric discharge machine, and constructing a data set to be distributed based on the machining precision data information of each machined part;
acquiring the machining precision evaluation grade of each mirror surface electric discharge machine according to the machining precision membership degree of the corrected mirror surface electric discharge machine;
meanwhile, classifying the machining precision of each machined part in the data set to be distributed through a fuzzy clustering algorithm AND an AND algorithm to obtain the machining precision evaluation grade of each machined part;
Fitting is carried out according to the machining precision evaluation grade of each machined part and the machining precision evaluation grade of each mirror surface electric discharge machine, and a production scheduling result is generated.
Further, in a preferred embodiment of the present invention, the fitting is performed according to the machining precision evaluation level of each machined part and the machining precision evaluation level of each mirror electric discharge machine, to generate a production scheduling result, which specifically includes:
fitting according to the machining precision evaluation grade of each machined part and the machining precision evaluation grade of each mirror surface electric discharge machine, generating a machining distribution result of each machining precision type machined part, and acquiring real-time machining state information of the mirror surface electric discharge machine;
judging whether the real-time processing state information of the mirror surface electric discharge machine is preset processing state information or not, and taking the mirror surface processing machine with the real-time processing state information being the preset processing state information as an allocable processing resource when the real-time processing state information of the mirror surface electric discharge machine is the preset processing state information;
acquiring position information of an allocable processing resource, constructing an allocable visual equipment management diagram according to the position information of the allocable processing resource, and updating the allocable visual equipment management diagram at any time;
And generating the machining position of each machining precision type machined part based on the machining distribution result of each machining precision type machined part and the allocable visual equipment management diagram, and displaying the machining position according to a preset mode.
A second aspect of the present invention provides a production scheduling system of a mirror electric discharge machine, the system including a memory and a processor, the memory including therein a production scheduling method program of the mirror electric discharge machine, the production scheduling method program of the mirror electric discharge machine, when executed by the processor, implementing the steps of:
acquiring machining precision state information of each mirror surface electric discharge machine of a current enterprise, and predicting machining precision state information within the next preset time according to the machining precision state information of the mirror surface electric discharge machine;
introducing a fuzzy clustering algorithm, and performing fuzzy clustering on the mirror surface electric discharge machining machines according to machining precision state information within the next preset time through the fuzzy clustering algorithm to generate a final clustering center and machining precision membership of each mirror surface electric discharge machining machine;
introducing an AND algorithm, AND correcting the machining precision membership of the mirror surface electric discharge machine through the AND algorithm to obtain the machining precision membership of the corrected mirror surface electric discharge machine;
And acquiring production order information of the mirror surface electric discharge machine, and generating a production scheduling result according to the machining precision membership degree of the corrected mirror surface electric discharge machine and the production order information of the mirror surface electric discharge machine.
In the system, the method for obtaining the machining precision state information of each mirror surface electric discharge machine of the current enterprise and estimating the machining precision state information within the next preset time according to the machining precision state information of the mirror surface electric discharge machine specifically comprises the following steps:
acquiring machining precision state information of each mirror surface electric discharge machine of a current enterprise, constructing a time stamp, combining the time stamp and the machining precision state information of each mirror surface electric discharge machine of the current enterprise to construct machining precision state information of each mirror surface electric discharge machine based on a time sequence, and storing the machining precision state information in a database;
acquiring machining precision state information of each mirror surface electric discharge machine based on a time sequence through the database, constructing a machining precision state prediction model based on a convolutional neural network, and constructing a feature matrix according to the machining precision state information of each mirror surface electric discharge machine based on the time sequence;
introducing a singular value decomposition algorithm into a convolution layer, processing the feature matrix through the singular value decomposition algorithm to generate a covariance matrix, inputting the covariance matrix into a pooling layer and a full-connection layer, identifying through an output vector, classifying through Softmax, storing model parameters, and outputting a processing precision state prediction model;
The method comprises the steps of obtaining machining precision state information of each mirror surface electric discharge machine within preset time, inputting the machining precision state information of each mirror surface electric discharge machine within the preset time into the machining precision state prediction model, and obtaining machining precision state information within the next preset time.
In the system, a fuzzy clustering algorithm is introduced, and the fuzzy clustering algorithm is used for carrying out fuzzy clustering on the mirror surface electric discharge machining machines according to the machining precision state information within the next preset time to generate a final clustering center and machining precision membership degree of each mirror surface electric discharge machining machine, and the system specifically comprises the following steps:
constructing a machining precision sample data set of the mirror surface electric discharge machine based on the machining precision state information within the next preset time, introducing a fuzzy clustering algorithm, initializing the range of a clustering center, introducing a genetic algorithm, and setting the number of chromosomes, the maximum iteration factor and the learning factor;
setting the clustering number, iteration termination condition, maximum iteration times, gaussian kernel number, gaussian kernel parameters and constraint coefficients according to a processing precision sample data set of the mirror surface electric discharge machine, and continuously updating a clustering center and a membership matrix through an objective function of the fuzzy clustering algorithm;
Stopping iteration when the maximum iteration times are reached, acquiring a corresponding membership matrix, acquiring a clustering center in the corresponding membership matrix, and taking the clustering center in the corresponding membership matrix as an optimal clustering center;
and generating a final clustering center and machining precision membership degrees of each mirror surface electric discharge machine according to the corresponding membership degree matrix and the optimal clustering center.
In the system, an AND algorithm is introduced, the machining precision membership of the mirror surface electric discharge machine is corrected through the AND algorithm, AND the corrected machining precision membership of the mirror surface electric discharge machine is obtained, AND the method specifically comprises the following steps:
introducing an AND algorithm, acquiring position nodes of each sample data in a machining precision sample data set of the mirror surface electric discharge machine, AND presetting a plurality of similarity indexes;
calculating a node evolution vector of a position node of each sample data in a processing precision sample data set of the mirror surface electric discharge machine under different similarity indexes;
performing abnormal evolution judgment on the node evolution vector through vector cosine similarity, obtaining an abnormal evolution node, constructing an abnormal evolution set, and inputting the abnormal evolution node into the abnormal evolution set;
Sample data corresponding to the abnormal evolution nodes in the abnormal evolution set are obtained, the sample data are redistributed to the class clusters corresponding to other clustering centers until the abnormal evolution nodes are not generated, and the machining precision membership of the mirror surface electric discharge machine after correction is generated.
The invention solves the defects existing in the background technology, and has the following beneficial effects:
the invention further introduces a fuzzy clustering algorithm by acquiring the machining precision state information of each mirror surface electric discharge machine of the current enterprise AND estimating the machining precision state information within the next preset time according to the machining precision state information of the mirror surface electric discharge machine, AND performs fuzzy clustering on the mirror surface electric discharge machines according to the machining precision state information within the next preset time through the fuzzy clustering algorithm to generate a final clustering center AND the machining precision membership degree of each mirror surface electric discharge machine, further introduces an AND algorithm, corrects the machining precision membership degree of the mirror surface electric discharge machine through the AND algorithm to acquire the machining precision membership degree of the mirror surface electric discharge machine after correction, AND finally generates a production scheduling result according to the machining precision membership degree of the mirror surface electric discharge machine after correction AND the production order information of the mirror surface electric discharge machine. The invention improves the fuzzy clustering algorithm by introducing the AND algorithm, AND can improve the clustering precision, thereby improving the distribution precision of the mirror surface electric discharge machine in the production scheduling process; and secondly, the invention fully considers the processing precision change of the mirror surface electric discharge machine, thereby optimizing the production schedule according to the processing precision data and improving the rationality of the production schedule.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows an overall method flow diagram of a production scheduling method of a mirror electric discharge machine;
FIG. 2 shows a first method flow chart of a method of scheduling production of a mirror electric discharge machine;
FIG. 3 shows a second method flow chart of a method of scheduling production of a mirror electric discharge machine;
fig. 4 shows a system block diagram of a production scheduling system of a mirror electric discharge machine.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
As shown in fig. 1, a first aspect of the present invention provides a production scheduling method of a mirror electric discharge machine, comprising the steps of:
s102, acquiring machining precision state information of each mirror surface electric discharge machine of a current enterprise, and estimating machining precision state information within the next preset time according to the machining precision state information of the mirror surface electric discharge machine;
as shown in fig. 2, in step S102, the following steps are specifically included:
s202, acquiring machining precision state information of each mirror surface electric discharge machine of a current enterprise, constructing a time stamp, combining the time stamp and the machining precision state information of each mirror surface electric discharge machine of the current enterprise to construct machining precision state information of each mirror surface electric discharge machine based on a time sequence, and storing the machining precision state information in a database;
s204, acquiring machining precision state information of each mirror surface electric discharge machine based on a time sequence through a database, constructing a machining precision state prediction model based on a convolutional neural network, and constructing a feature matrix according to the machining precision state information of each mirror surface electric discharge machine based on the time sequence;
S206, introducing a singular value decomposition algorithm into the convolution layer, processing the feature matrix through the singular value decomposition algorithm to generate a covariance matrix, inputting the covariance matrix into the pooling layer and the full-connection layer, identifying through an output vector, classifying through Softmax, storing model parameters, and outputting a processing precision state prediction model;
s208, acquiring machining precision state information of each mirror surface electric discharge machine within preset time, inputting the machining precision state information of each mirror surface electric discharge machine within the preset time into a machining precision state prediction model, and acquiring the machining precision state information within the next preset time.
First, since the machining accuracy tends to be low during the service of the mirror electric discharge machine, the machining accuracy tends to be poor, and the mirror electric discharge machine is likely to be in a failure state. The method can predict the processing precision state information of each mirror processing machine in the current enterprise within the next preset time. And secondly, according to the method, the singular value decomposition algorithm is introduced into the convolution layer to perform data dimension reduction processing, so that the operation amount of the processing precision state prediction model in prediction can be improved, and the operation speed of the model is improved.
S104, introducing a fuzzy clustering algorithm, and performing fuzzy clustering on the mirror surface electric discharge machining machines according to machining precision state information within the next preset time through the fuzzy clustering algorithm to generate a final clustering center and machining precision membership of each mirror surface electric discharge machining machine;
in step S104, the method specifically includes:
constructing a machining precision sample data set of the mirror surface electric discharge machine based on machining precision state information within the next preset time, introducing a fuzzy clustering algorithm, initializing a range of a clustering center, introducing a genetic algorithm, and setting the number of chromosomes, the maximum iteration factor and a learning factor;
setting the clustering number, iteration termination condition, maximum iteration times, gaussian kernel number, gaussian kernel parameters and constraint coefficients according to a processing precision sample data set of the mirror surface electric discharge machine, and continuously updating a clustering center and a membership matrix through an objective function of a fuzzy clustering algorithm;
stopping iteration when the maximum iteration times are reached, acquiring a corresponding membership matrix, acquiring a clustering center in the corresponding membership matrix, and taking the clustering center in the corresponding membership matrix as an optimal clustering center;
And generating a final cluster center and machining precision membership degrees of each mirror surface electric discharge machine according to the corresponding membership degree matrix and the optimal cluster center.
It should be noted that, the machining precision of the mirror surface machining machines of different models is inconsistent, and the machining precision of different service times of the same model is inconsistent, and by the method, the machining precision of all the mirror surface electric discharge machines of enterprises can be rapidly converged, so that the rapidity of production scheduling is improved. Secondly, a genetic algorithm is introduced to carry out iterative selection on fuzzy clustering algorithm, so that the number of suitable clustering centers is selected, the situation of sinking into a local optimal solution is effectively avoided, wherein the machining precision membership degree of the mirror surface electric discharge machine represents the machining precision grade of the mirror surface electric discharge machine, such as low machining precision grade, low and medium machining precision grade, machining precision grade and the like, the processing speed of production data is accelerated, and a production scheduling scheme can be rapidly generated.
S106, introducing an AND algorithm, AND correcting the machining precision membership of the mirror surface electric discharge machine through the AND algorithm to obtain the machining precision membership of the corrected mirror surface electric discharge machine;
In step S106, the method specifically includes:
introducing an AND algorithm, acquiring position nodes of each sample data in a machining precision sample data set of the mirror surface electric discharge machine, AND presetting a plurality of similarity indexes;
calculating a node evolution vector of a position node of each sample data in a processing precision sample data set of the mirror surface electric discharge machine under different similarity indexes;
carrying out abnormal evolution judgment on the node evolution vector through vector cosine similarity, obtaining an abnormal evolution node, constructing an abnormal evolution set, and inputting the abnormal evolution node into the abnormal evolution set;
sample data corresponding to the abnormal evolution nodes in the abnormal evolution set are obtained, the sample data are redistributed to the class clusters corresponding to other clustering centers until the abnormal evolution nodes are not generated, and the machining precision membership of the mirror surface electric discharge machine after correction is generated.
It should be noted that, the method can calculate the node evolution vector of the position node of each sample data in the processing precision sample data set of the mirror surface electric discharge machine under different similarity indexes by introducing an AND algorithm, so as to select the sample data of abnormal classification, AND redistribute the sample data into the class clusters corresponding to other clustering centers, thereby finishing the correction of the processing precision membership degree of the mirror surface electric discharge machine.
S108, obtaining production order information of the mirror surface electric discharge machine, and generating a production scheduling result according to the machining precision membership degree of the mirror surface electric discharge machine after correction and the production order information of the mirror surface electric discharge machine.
In step S108, the method specifically includes:
acquiring production order information of the mirror surface electric discharge machine, acquiring machining precision data information of each machined part according to the production order information of the mirror surface electric discharge machine, and constructing a data set to be distributed based on the machining precision data information of each machined part;
acquiring the machining precision evaluation grade of each mirror surface electric discharge machine according to the machining precision membership degree of the corrected mirror surface electric discharge machine;
meanwhile, classifying the machining precision of each machined part in the data set to be distributed through a fuzzy clustering algorithm AND an AND algorithm to obtain the machining precision evaluation grade of each machined part;
fitting is carried out according to the machining precision evaluation grade of each machined part and the machining precision evaluation grade of each mirror surface electric discharge machine, and a production scheduling result is generated.
The processing precision of each processed part in the data set to be distributed is classified through a fuzzy clustering algorithm AND an AND algorithm, so that the processing precision evaluation grade of each processed part is obtained, the processing precision evaluation grade of each processed part is consistent with the processing precision membership degree generation mode of the mirror surface electric discharge machine, AND therefore the processing precision evaluation grade of each processed part can be generated according to the processing precision membership degree of the processed part, AND sample data of the processed part can be rapidly processed. The production order information of the mirror surface electric discharge machine comprises drawing paper, processing time, processing precision data and the like of the processed parts.
As shown in fig. 3, fitting is performed according to the machining precision evaluation level of each machined part and the machining precision evaluation level of each mirror surface electric discharge machine to generate a production scheduling result, and specifically includes:
s302, fitting according to the machining precision evaluation grade of each machined part and the machining precision evaluation grade of each mirror surface electric discharge machine, generating a machining distribution result of each machining precision type machined part, and acquiring real-time machining state information of the mirror surface electric discharge machine;
s304, judging whether the real-time processing state information of the mirror surface electric discharge machine is preset processing state information, and when the real-time processing state information of the mirror surface electric discharge machine is the preset processing state information, taking the mirror surface processing machine with the real-time processing state information being the preset processing state information as an allocable processing resource;
s306, acquiring position information of the allocable processing resources, constructing an allocable visual equipment management diagram according to the position information of the allocable processing resources, and updating the allocable visual equipment management diagram at any time;
and S308, generating the machining position of each machining precision type machined part based on the machining distribution result of each machining precision type machined part and an allocable visual equipment management chart, and displaying the machining position according to a preset mode.
The fitting is performed according to the machining precision evaluation level of each machined part and the machining precision evaluation level of each mirror surface electric discharge machine, and when the machining precision evaluation level of each machined part is smaller than or equal to the machining precision evaluation level of each mirror surface electric discharge machine, the corresponding mirror surface machining equipment is described as the machining equipment of the part; on the contrary, the device cannot be used as a processing device for the part. The method can be used for rapidly distributing the processing equipment according to the processing precision data of the parts, so that the distribution of the processing equipment is more reasonable, the position of the processing equipment can be displayed, the position of the equipment can be rapidly prompted, and a user can conveniently process the corresponding parts. Wherein the preset machining state is a mirror-surface electric discharge machine capable of normal machining and is not a mirror-surface electric discharge machine in a machining state.
In summary, the invention improves the fuzzy clustering algorithm by introducing the AND algorithm, AND can improve the clustering precision, thereby improving the distribution precision of the mirror surface electric discharge machine in the production scheduling process; and secondly, the invention fully considers the processing precision change of the mirror surface electric discharge machine, thereby optimizing the production schedule according to the processing precision data and improving the rationality of the production schedule.
In addition, the invention can also comprise the following steps:
acquiring service state data information of each mirror surface electric discharge machine of a current enterprise, presetting a plurality of machining state thresholds, and classifying the service state data information of each mirror surface electric discharge machine of the current enterprise according to the machining state thresholds; the processing state threshold value comprises a processing state which can be processed normally, a processing state which is being maintained and a processing state in the maintenance process;
the method comprises the steps of obtaining the machining state category of each classified mirror surface electric discharge machine after classification, selecting a mirror surface machining machine with a machining state which can be machined normally from the machining state category of the classified mirror surface electric discharge machine as an allocable machining resource, and updating the allocable machining resource at any time;
constructing an allocable resource database, acquiring server id information of each mirror finishing machine in allocable processing resources, and introducing an attention mechanism to calculate the attention score of the server id information of each mirror finishing machine in the allocable processing resources;
and sorting the server id information of each mirror finishing machine in the allocable processing resources from big to small according to the attention score, obtaining a sorting result, and sequentially inputting the sorting result into the allocable resource database for storage according to the sorting result.
By the method, the allocable processing resources can be more accurately identified according to actual conditions, and the rationality of production scheduling is improved, so that the allocable resource data are sequentially input into the allocable resource database for storage according to the sequencing result, and the query speed of the allocable resource data is improved.
In addition, the method can further comprise the following steps:
acquiring working environment information of a current mirror surface processing machine through big data, analyzing the correlation of the working environment information on the processing precision of the mirror surface electric discharge processing machine through a multi-factor logistic regression analysis method, and acquiring corresponding influence weight vector information;
introducing a gray correlation analysis method, and analyzing the corresponding influence weight vector information through the gray correlation analysis method to obtain the influence evaluation score of each environmental factor on the machining precision of the mirror surface electric discharge machine;
judging whether the evaluation score is larger than a preset evaluation score, and if the evaluation score is larger than the preset evaluation score, acquiring offset information of the machining precision of the mirror surface electric discharge machine under the working environment information of the current mirror surface machining machine through big data;
and dynamically correcting the machining precision of each mirror surface machining machine according to the offset information of the machining precision of the mirror surface electric discharge machining machine under the working environment information of the current mirror surface machining machine.
The method can dynamically correct the machining precision of each mirror surface machining machine according to the offset information of the machining precision of the mirror surface electric discharge machining machine under the working environment information of the current mirror surface machining machine, so that the prediction accuracy of the machining precision of the mirror surface machining machine is improved, the rationality of production scheduling of production orders is improved, and the generation of defective products is reduced. The working environment information includes temperature, humidity, dust level, etc.
As shown in fig. 4, a second aspect of the present invention provides a production scheduling system 4 of a mirror electric discharge machine, the system including a memory 41 and a processor 62, the memory 41 including a production scheduling method program of the mirror electric discharge machine, the production scheduling method program of the mirror electric discharge machine, when executed by the processor 62, implementing the steps of:
acquiring machining precision state information of each mirror surface electric discharge machine of a current enterprise, and predicting machining precision state information within the next preset time according to the machining precision state information of the mirror surface electric discharge machine;
introducing a fuzzy clustering algorithm, and performing fuzzy clustering on the mirror surface electric discharge machining machines according to machining precision state information within the next preset time through the fuzzy clustering algorithm to generate a final clustering center and machining precision membership of each mirror surface electric discharge machining machine;
Introducing an AND algorithm, AND correcting the machining precision membership of the mirror surface electric discharge machine through the AND algorithm to obtain the machining precision membership of the corrected mirror surface electric discharge machine;
and acquiring production order information of the mirror surface electric discharge machine, and generating a production scheduling result according to the machining precision membership degree of the mirror surface electric discharge machine after correction and the production order information of the mirror surface electric discharge machine.
In the system, the processing precision state information of each mirror surface electric discharge machine of the current enterprise is obtained, and the processing precision state information within the next preset time is estimated according to the processing precision state information of the mirror surface electric discharge machine, and the system specifically comprises the following steps:
acquiring machining precision state information of each mirror surface electric discharge machine of a current enterprise, constructing a time stamp, combining the time stamp and the machining precision state information of each mirror surface electric discharge machine of the current enterprise to construct machining precision state information of each mirror surface electric discharge machine based on a time sequence, and storing the machining precision state information in a database;
acquiring machining precision state information of each mirror surface electric discharge machine based on a time sequence through a database, constructing a machining precision state prediction model based on a convolutional neural network, and constructing a feature matrix according to the machining precision state information of each mirror surface electric discharge machine based on the time sequence;
Introducing a singular value decomposition algorithm into the convolution layer, processing the feature matrix through the singular value decomposition algorithm to generate a covariance matrix, inputting the covariance matrix into the pooling layer and the full-connection layer, identifying through an output vector, classifying through Softmax, storing model parameters, and outputting a processing precision state prediction model;
the method comprises the steps of obtaining machining precision state information of each mirror surface electric discharge machine within preset time, inputting the machining precision state information of each mirror surface electric discharge machine within the preset time into a machining precision state prediction model, and obtaining machining precision state information within the next preset time.
In the system, a fuzzy clustering algorithm is introduced, and the mirror surface electric discharge machining machines are subjected to fuzzy clustering according to the machining precision state information within the next preset time through the fuzzy clustering algorithm, so that a final clustering center and the machining precision membership degree of each mirror surface electric discharge machining machine are generated, and the system specifically comprises the following steps:
constructing a machining precision sample data set of the mirror surface electric discharge machine based on machining precision state information within the next preset time, introducing a fuzzy clustering algorithm, initializing a range of a clustering center, introducing a genetic algorithm, and setting the number of chromosomes, the maximum iteration factor and a learning factor;
Setting the clustering number, iteration termination condition, maximum iteration times, gaussian kernel number, gaussian kernel parameters and constraint coefficients according to a processing precision sample data set of the mirror surface electric discharge machine, and continuously updating a clustering center and a membership matrix through an objective function of a fuzzy clustering algorithm;
stopping iteration when the maximum iteration times are reached, acquiring a corresponding membership matrix, acquiring a clustering center in the corresponding membership matrix, and taking the clustering center in the corresponding membership matrix as an optimal clustering center;
and generating a final cluster center and machining precision membership degrees of each mirror surface electric discharge machine according to the corresponding membership degree matrix and the optimal cluster center.
In the system, an AND algorithm is introduced, AND the machining precision membership of the mirror surface electric discharge machine is corrected through the AND algorithm, so that the machining precision membership of the corrected mirror surface electric discharge machine is obtained, AND the method specifically comprises the following steps:
introducing an AND algorithm, acquiring position nodes of each sample data in a machining precision sample data set of the mirror surface electric discharge machine, AND presetting a plurality of similarity indexes;
calculating a node evolution vector of a position node of each sample data in a processing precision sample data set of the mirror surface electric discharge machine under different similarity indexes;
Carrying out abnormal evolution judgment on the node evolution vector through vector cosine similarity, obtaining an abnormal evolution node, constructing an abnormal evolution set, and inputting the abnormal evolution node into the abnormal evolution set;
sample data corresponding to the abnormal evolution nodes in the abnormal evolution set are obtained, the sample data are redistributed to the class clusters corresponding to other clustering centers until the abnormal evolution nodes are not generated, and the machining precision membership of the mirror surface electric discharge machine after correction is generated.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. A production scheduling method of a mirror surface electric discharge machine, comprising the steps of:
acquiring machining precision state information of each mirror surface electric discharge machine of a current enterprise, and predicting machining precision state information within the next preset time according to the machining precision state information of the mirror surface electric discharge machine;
introducing a fuzzy clustering algorithm, and performing fuzzy clustering on the mirror surface electric discharge machining machines according to machining precision state information within the next preset time through the fuzzy clustering algorithm to generate a final clustering center and machining precision membership of each mirror surface electric discharge machining machine;
introducing an AND algorithm, AND correcting the machining precision membership of the mirror surface electric discharge machine through the AND algorithm to obtain the machining precision membership of the corrected mirror surface electric discharge machine;
and acquiring production order information of the mirror surface electric discharge machine, and generating a production scheduling result according to the machining precision membership degree of the corrected mirror surface electric discharge machine and the production order information of the mirror surface electric discharge machine.
2. The method for manufacturing and dispatching a mirror electric discharge machine according to claim 1, wherein the step of obtaining machining precision state information of each mirror electric discharge machine of a current enterprise and estimating machining precision state information within a next preset time according to the machining precision state information of the mirror electric discharge machine comprises the steps of:
Acquiring machining precision state information of each mirror surface electric discharge machine of a current enterprise, constructing a time stamp, combining the time stamp and the machining precision state information of each mirror surface electric discharge machine of the current enterprise to construct machining precision state information of each mirror surface electric discharge machine based on a time sequence, and storing the machining precision state information in a database;
acquiring machining precision state information of each mirror surface electric discharge machine based on a time sequence through the database, constructing a machining precision state prediction model based on a convolutional neural network, and constructing a feature matrix according to the machining precision state information of each mirror surface electric discharge machine based on the time sequence;
introducing a singular value decomposition algorithm into a convolution layer, processing the feature matrix through the singular value decomposition algorithm to generate a covariance matrix, inputting the covariance matrix into a pooling layer and a full-connection layer, identifying through an output vector, classifying through Softmax, storing model parameters, and outputting a processing precision state prediction model;
the method comprises the steps of obtaining machining precision state information of each mirror surface electric discharge machine within preset time, inputting the machining precision state information of each mirror surface electric discharge machine within the preset time into the machining precision state prediction model, and obtaining machining precision state information within the next preset time.
3. The method according to claim 1, wherein the step of introducing a fuzzy clustering algorithm, and performing fuzzy clustering on the mirror surface electric discharge machine according to machining precision state information within a next preset time by using the fuzzy clustering algorithm, to generate a final clustering center and machining precision membership of each mirror surface electric discharge machine, comprises the following steps:
constructing a machining precision sample data set of the mirror surface electric discharge machine based on the machining precision state information within the next preset time, introducing a fuzzy clustering algorithm, initializing the range of a clustering center, introducing a genetic algorithm, and setting the number of chromosomes, the maximum iteration factor and the learning factor;
setting the clustering number, iteration termination condition, maximum iteration times, gaussian kernel number, gaussian kernel parameters and constraint coefficients according to a processing precision sample data set of the mirror surface electric discharge machine, and continuously updating a clustering center and a membership matrix through an objective function of the fuzzy clustering algorithm;
stopping iteration when the maximum iteration times are reached, acquiring a corresponding membership matrix, acquiring a clustering center in the corresponding membership matrix, and taking the clustering center in the corresponding membership matrix as an optimal clustering center;
And generating a final clustering center and machining precision membership degrees of each mirror surface electric discharge machine according to the corresponding membership degree matrix and the optimal clustering center.
4. The production scheduling method of a mirror electric discharge machine according to claim 1, wherein the introducing an AND algorithm corrects the machining accuracy membership of the mirror electric discharge machine by the AND algorithm to obtain the corrected machining accuracy membership of the mirror electric discharge machine, AND specifically comprises:
introducing an AND algorithm, acquiring position nodes of each sample data in a machining precision sample data set of the mirror surface electric discharge machine, AND presetting a plurality of similarity indexes;
calculating a node evolution vector of a position node of each sample data in a processing precision sample data set of the mirror surface electric discharge machine under different similarity indexes;
performing abnormal evolution judgment on the node evolution vector through vector cosine similarity, obtaining an abnormal evolution node, constructing an abnormal evolution set, and inputting the abnormal evolution node into the abnormal evolution set;
sample data corresponding to the abnormal evolution nodes in the abnormal evolution set are obtained, the sample data are redistributed to the class clusters corresponding to other clustering centers until the abnormal evolution nodes are not generated, and the machining precision membership of the mirror surface electric discharge machine after correction is generated.
5. The method according to claim 1, wherein the step of obtaining production order information of the mirror electric discharge machine and generating a production scheduling result according to the machining precision membership of the mirror electric discharge machine after correction and the production order information of the mirror electric discharge machine, comprises:
acquiring production order information of a mirror surface electric discharge machine, acquiring machining precision data information of each machined part according to the production order information of the mirror surface electric discharge machine, and constructing a data set to be distributed based on the machining precision data information of each machined part;
acquiring the machining precision evaluation grade of each mirror surface electric discharge machine according to the machining precision membership degree of the corrected mirror surface electric discharge machine;
meanwhile, classifying the machining precision of each machined part in the data set to be distributed through a fuzzy clustering algorithm AND an AND algorithm to obtain the machining precision evaluation grade of each machined part;
fitting is carried out according to the machining precision evaluation grade of each machined part and the machining precision evaluation grade of each mirror surface electric discharge machine, and a production scheduling result is generated.
6. The method according to claim 5, wherein the fitting is performed according to the machining precision evaluation level of each machined part and the machining precision evaluation level of each mirror electric discharge machine to generate a production scheduling result, specifically comprising:
fitting according to the machining precision evaluation grade of each machined part and the machining precision evaluation grade of each mirror surface electric discharge machine, generating a machining distribution result of each machining precision type machined part, and acquiring real-time machining state information of the mirror surface electric discharge machine;
judging whether the real-time processing state information of the mirror surface electric discharge machine is preset processing state information or not, and taking the mirror surface processing machine with the real-time processing state information being the preset processing state information as an allocable processing resource when the real-time processing state information of the mirror surface electric discharge machine is the preset processing state information;
acquiring position information of an allocable processing resource, constructing an allocable visual equipment management diagram according to the position information of the allocable processing resource, and updating the allocable visual equipment management diagram at any time;
And generating the machining position of each machining precision type machined part based on the machining distribution result of each machining precision type machined part and the allocable visual equipment management diagram, and displaying the machining position according to a preset mode.
7. A production scheduling system of a mirror electric discharge machine, characterized in that the system comprises a memory and a processor, wherein the memory comprises a production scheduling method program of the mirror electric discharge machine, and when the production scheduling method program of the mirror electric discharge machine is executed by the processor, the following steps are realized:
acquiring machining precision state information of each mirror surface electric discharge machine of a current enterprise, and predicting machining precision state information within the next preset time according to the machining precision state information of the mirror surface electric discharge machine;
introducing a fuzzy clustering algorithm, and performing fuzzy clustering on the mirror surface electric discharge machining machines according to machining precision state information within the next preset time through the fuzzy clustering algorithm to generate a final clustering center and machining precision membership of each mirror surface electric discharge machining machine;
introducing an AND algorithm, AND correcting the machining precision membership of the mirror surface electric discharge machine through the AND algorithm to obtain the machining precision membership of the corrected mirror surface electric discharge machine;
And acquiring production order information of the mirror surface electric discharge machine, and generating a production scheduling result according to the machining precision membership degree of the corrected mirror surface electric discharge machine and the production order information of the mirror surface electric discharge machine.
8. The system according to claim 7, wherein the step of obtaining the machining precision state information of each mirror electric discharge machine of the current enterprise and estimating the machining precision state information within the next preset time according to the machining precision state information of the mirror electric discharge machine comprises:
acquiring machining precision state information of each mirror surface electric discharge machine of a current enterprise, constructing a time stamp, combining the time stamp and the machining precision state information of each mirror surface electric discharge machine of the current enterprise to construct machining precision state information of each mirror surface electric discharge machine based on a time sequence, and storing the machining precision state information in a database;
acquiring machining precision state information of each mirror surface electric discharge machine based on a time sequence through the database, constructing a machining precision state prediction model based on a convolutional neural network, and constructing a feature matrix according to the machining precision state information of each mirror surface electric discharge machine based on the time sequence;
Introducing a singular value decomposition algorithm into a convolution layer, processing the feature matrix through the singular value decomposition algorithm to generate a covariance matrix, inputting the covariance matrix into a pooling layer and a full-connection layer, identifying through an output vector, classifying through Softmax, storing model parameters, and outputting a processing precision state prediction model;
the method comprises the steps of obtaining machining precision state information of each mirror surface electric discharge machine within preset time, inputting the machining precision state information of each mirror surface electric discharge machine within the preset time into the machining precision state prediction model, and obtaining machining precision state information within the next preset time.
9. The production scheduling system of claim 7, wherein the introducing a fuzzy clustering algorithm, by which the mirror electric discharge machine is fuzzy clustered according to the machining precision state information within the next preset time, generates a final cluster center and a machining precision membership degree of each mirror electric discharge machine, specifically comprises:
constructing a machining precision sample data set of the mirror surface electric discharge machine based on the machining precision state information within the next preset time, introducing a fuzzy clustering algorithm, initializing the range of a clustering center, introducing a genetic algorithm, and setting the number of chromosomes, the maximum iteration factor and the learning factor;
Setting the clustering number, iteration termination condition, maximum iteration times, gaussian kernel number, gaussian kernel parameters and constraint coefficients according to a processing precision sample data set of the mirror surface electric discharge machine, and continuously updating a clustering center and a membership matrix through an objective function of the fuzzy clustering algorithm;
stopping iteration when the maximum iteration times are reached, acquiring a corresponding membership matrix, acquiring a clustering center in the corresponding membership matrix, and taking the clustering center in the corresponding membership matrix as an optimal clustering center;
and generating a final clustering center and machining precision membership degrees of each mirror surface electric discharge machine according to the corresponding membership degree matrix and the optimal clustering center.
10. The production scheduling system of a mirror electric discharge machine according to claim 7, wherein the introducing an AND algorithm corrects the machining accuracy membership of the mirror electric discharge machine by the AND algorithm to obtain the corrected machining accuracy membership of the mirror electric discharge machine, AND specifically comprises:
introducing an AND algorithm, acquiring position nodes of each sample data in a machining precision sample data set of the mirror surface electric discharge machine, AND presetting a plurality of similarity indexes;
Calculating a node evolution vector of a position node of each sample data in a processing precision sample data set of the mirror surface electric discharge machine under different similarity indexes;
performing abnormal evolution judgment on the node evolution vector through vector cosine similarity, obtaining an abnormal evolution node, constructing an abnormal evolution set, and inputting the abnormal evolution node into the abnormal evolution set;
sample data corresponding to the abnormal evolution nodes in the abnormal evolution set are obtained, the sample data are redistributed to the class clusters corresponding to other clustering centers until the abnormal evolution nodes are not generated, and the machining precision membership of the mirror surface electric discharge machine after correction is generated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310959932.8A CN116681266B (en) | 2023-08-02 | 2023-08-02 | Production scheduling method and system of mirror surface electric discharge machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310959932.8A CN116681266B (en) | 2023-08-02 | 2023-08-02 | Production scheduling method and system of mirror surface electric discharge machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116681266A true CN116681266A (en) | 2023-09-01 |
| CN116681266B CN116681266B (en) | 2024-02-02 |
Family
ID=87791348
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310959932.8A Active CN116681266B (en) | 2023-08-02 | 2023-08-02 | Production scheduling method and system of mirror surface electric discharge machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116681266B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6980959B1 (en) * | 2000-10-17 | 2005-12-27 | Accenture Llp | Configuring mechanical equipment |
| CN106774144A (en) * | 2016-12-21 | 2017-05-31 | 上海华括自动化工程有限公司 | A kind of intelligent CNC processing methods based on industrial robot |
| CN107918814A (en) * | 2017-12-14 | 2018-04-17 | 上海电机学院 | A kind of manufacturing resource allocation method towards low-carbon process planning |
| CN108053138A (en) * | 2017-12-27 | 2018-05-18 | 华侨大学 | A kind of community manufacture system manufacturing service capability assessment method towards order demand |
| CN113553493A (en) * | 2020-04-24 | 2021-10-26 | 哈尔滨工业大学 | Service selection method based on demand service probability matrix |
| CN115345485A (en) * | 2022-08-17 | 2022-11-15 | 珠海爱浦京软件股份有限公司 | Intelligent factory equipment data analysis management system and method based on big data |
| CN115641097A (en) * | 2022-12-23 | 2023-01-24 | 深圳市仕瑞达自动化设备有限公司 | Non-standard machining collaborative manufacturing management method and system based on cloud platform |
| CN115994619A (en) * | 2022-12-28 | 2023-04-21 | 中车信息技术有限公司 | Intelligent generation method for part machining process route |
-
2023
- 2023-08-02 CN CN202310959932.8A patent/CN116681266B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6980959B1 (en) * | 2000-10-17 | 2005-12-27 | Accenture Llp | Configuring mechanical equipment |
| CN106774144A (en) * | 2016-12-21 | 2017-05-31 | 上海华括自动化工程有限公司 | A kind of intelligent CNC processing methods based on industrial robot |
| CN107918814A (en) * | 2017-12-14 | 2018-04-17 | 上海电机学院 | A kind of manufacturing resource allocation method towards low-carbon process planning |
| CN108053138A (en) * | 2017-12-27 | 2018-05-18 | 华侨大学 | A kind of community manufacture system manufacturing service capability assessment method towards order demand |
| CN113553493A (en) * | 2020-04-24 | 2021-10-26 | 哈尔滨工业大学 | Service selection method based on demand service probability matrix |
| CN115345485A (en) * | 2022-08-17 | 2022-11-15 | 珠海爱浦京软件股份有限公司 | Intelligent factory equipment data analysis management system and method based on big data |
| CN115641097A (en) * | 2022-12-23 | 2023-01-24 | 深圳市仕瑞达自动化设备有限公司 | Non-standard machining collaborative manufacturing management method and system based on cloud platform |
| CN115994619A (en) * | 2022-12-28 | 2023-04-21 | 中车信息技术有限公司 | Intelligent generation method for part machining process route |
Non-Patent Citations (1)
| Title |
|---|
| 程丽军;王艳;: "面向云端融合的任务-资源双边匹配决策模型", 系统仿真学报, no. 11, pages 4348 - 4358 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116681266B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104881706B (en) | A kind of power-system short-term load forecasting method based on big data technology | |
| CN110297852B (en) | Ship coating defect knowledge acquisition method based on PCA-rough set | |
| Bodendorf et al. | A machine learning approach to estimate product costs in the early product design phase: a use case from the automotive industry | |
| CN111401642A (en) | Method, device and equipment for automatically adjusting predicted value and storage medium | |
| Hsu | Clustering ensemble for identifying defective wafer bin map in semiconductor manufacturing | |
| CN113111924A (en) | Electric power customer classification method and device | |
| CN115185247A (en) | Machine tool running state prediction and workshop scheduling method based on product processing quality | |
| Kou et al. | Binary particle swarm optimization-based association rule mining for discovering relationships between machine capabilities and product features | |
| CN117095247B (en) | Numerical control machining-based machining gesture operation optimization method, system and medium | |
| CN114781688A (en) | Method, device, equipment and storage medium for identifying abnormal data of business expansion project | |
| CN117010666B (en) | Intelligent management method and system for production workstation of automobile repair tool | |
| CN116681266B (en) | Production scheduling method and system of mirror surface electric discharge machine | |
| CN117056591A (en) | Intelligent electric power payment channel recommendation method and system based on dynamic prediction | |
| Schuh et al. | Databased prediction and planning of order-specific transition times | |
| Korytkowski | A genetic algorithm with tournament selection for optimising inspection allocation in multiproduct multistage production systems | |
| CN113592064B (en) | Ring polishing process parameter prediction method, system, application, terminal and medium | |
| CN113610575B (en) | Product sales prediction method and prediction system | |
| Piwowarski et al. | Issues of multi-criteria methods applicability supporting complex business process decision-making in management | |
| Kluska-Nawarecka et al. | Practical aspects of knowledge integration using attribute tables generated from relational databases | |
| CN112308340A (en) | Power data processing method and device | |
| CN111143774B (en) | Power load prediction method and device based on influence factor multi-state model | |
| CN113656294A (en) | Software defect prediction method | |
| CN112949908A (en) | Electricity price probability prediction method and device | |
| CN113610225A (en) | Quality evaluation model training method and device, electronic equipment and storage medium | |
| CN112579580A (en) | Pre-alarm method based on industrial big data prediction |
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 |