CN117273340A - Product and manufacturing data intelligent optimization method, device, equipment and storage medium - Google Patents
Product and manufacturing data intelligent optimization method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117273340A CN117273340A CN202311220646.6A CN202311220646A CN117273340A CN 117273340 A CN117273340 A CN 117273340A CN 202311220646 A CN202311220646 A CN 202311220646A CN 117273340 A CN117273340 A CN 117273340A
- Authority
- CN
- China
- Prior art keywords
- data
- change
- product
- time
- manufacturing
- 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.)
- Pending
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 212
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 238000005457 optimization Methods 0.000 title claims description 56
- 230000008859 change Effects 0.000 claims abstract description 369
- 238000013439 planning Methods 0.000 claims abstract description 67
- 238000012795 verification Methods 0.000 claims description 68
- 238000013461 design Methods 0.000 claims description 52
- 230000006870 function Effects 0.000 claims description 45
- 238000001914 filtration Methods 0.000 claims description 42
- 238000012549 training Methods 0.000 claims description 27
- 238000010801 machine learning Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 17
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000012986 modification Methods 0.000 claims description 8
- 230000004048 modification Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 2
- 239000000463 material Substances 0.000 abstract description 21
- 238000004891 communication Methods 0.000 abstract description 10
- 238000013496 data integrity verification Methods 0.000 abstract description 7
- 238000012384 transportation and delivery Methods 0.000 abstract description 6
- 239000002699 waste material Substances 0.000 abstract description 6
- 239000000047 product Substances 0.000 description 140
- 238000010586 diagram Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 10
- 238000007726 management method Methods 0.000 description 6
- 238000012423 maintenance Methods 0.000 description 4
- 238000012417 linear regression Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000007728 cost analysis Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method 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
- G06Q10/06313—Resource planning in a project environment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
- G06F16/2358—Change logging, detection, and notification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
- G06F16/2365—Ensuring data consistency and integrity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- 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
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/06316—Sequencing of tasks or work
-
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q10/0875—Itemisation or classification of parts, supplies or services, e.g. bill of materials
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
Abstract
The invention discloses a method, a device, equipment and a storage medium for intelligently optimizing product and manufacturing data, wherein the method is characterized in that historical BOM change data, project planning time data and project cost data are obtained; carrying out integrity check on the historical BOM change data to obtain target change data which is successfully checked; predicting the influence of the target change data on project planning time data and project cost data, obtaining a prediction result, generating a predictive suggestion according to the prediction result, and optimizing the product manufacturing process according to the predictive suggestion; the data integrity verification can be carried out, the data change workload and the data change error rate are reduced, and the time and cost loss is reduced; the BOM change can be accurately, efficiently and completely carried out, the product inventory can be reduced, the production efficiency is improved, delivery is guaranteed, the cost is reduced, the time of coordination and communication is reduced, and the waste of manpower and material resources is avoided.
Description
Technical Field
The present invention relates to the field of intelligent manufacturing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for intelligent optimization of product and manufacturing data.
Background
A large amount of product and manufacturing data has been accumulated in the long-term business production of enterprises; the core products and Manufacturing data of Manufacturing enterprises are bill of materials (Bill of Materials, BOM), from research and development stages of the products to mass production, the bill of materials undergoes evolution of product design (Engineering BOM, EBOM), manufacturing BOM, MBOM, process BOM, PBOM, cost BOM, CBOM, sales BOM, SBOM and the like, each BOM has different structures, different versions exist in different periods, and the covered content feature fields are also different, so that the overall complexity is high.
The development life cycle of a product can be as long as years, and the product parts can be frequently changed due to reasons of design optimization, synchronous engineering, cost reduction, supply chain replacement and the like from definition design, sample test, mass production manufacturing, release and subsequent product iteration.
The maintenance of the data is carried out for a long time, the personnel involved in various aspects change along with the continuous modification of the product, and the contents of the bill of materials are subjected to repeated revisions, retries and writing and are required to undergo repeated audits, so that the probability of errors of the contents of the bill of materials is greatly increased; therefore, the modification of the BOM is simplified, the processing efficiency of the modification, query and other operations of the BOM table is improved, and the improvement of the data integrity is a higher target pursued in the future.
Because of the increasingly strong market competition, the digital upgrade of future intelligent manufacturing, how to utilize idle historical industrial big data, promote project management and control, reduce the influence of product and manufacturing data change on time planning and cost, is the subject of continuous research.
The existing mode generally finds out the association between materials according to a material association table, firstly carries out cost analysis on a first layer of material of a convolution tree, finds out a lower-order material of the material, then carries out cost analysis on the lower-order material, carries out reason summarization aiming at cost influence factors of all levels until the branch material tree is traversed, then carries out mining on a second layer of material of the first layer of the convolution tree, and then has the same logic as before. The output impact value logic outputs according to the mining logic.
However, in the existing product and manufacturing data processing, various BOMs are compiled and maintained by multiple departments and personnel, so that manual verification and compiling are needed, the workload is high, and errors are easy to occur; when the product design is changed, the change of corresponding parts such as a process BOM, a manufacturing BOM, a boxing BOM, an after-sales BOM and the like is difficult to be quickly found, so that the version configuration is numerous, and the economic loss caused by inconsistent final products is easy to cause; hidden relationships are difficult to define and explore.
Disclosure of Invention
The invention mainly aims to provide a product and manufacturing data intelligent optimization method, device, equipment and storage medium, and aims to solve the technical problems that in the prior art, the manual auditing and writing workload is large, errors are easy to occur in product and manufacturing data processing, economic loss caused by inconsistent final products is easy to occur when product design is changed, the error rate of data change is high, the influence of data change on project time and cost is large, and the data value is easy to lose.
In a first aspect, the present invention provides a method for intelligently optimizing product and manufacturing data, the method comprising the steps of:
acquiring historical BOM change data, project planning time data and project cost data;
carrying out integrity check on the historical BOM change data to obtain target change data which is successfully checked;
predicting the influence of the target change data on project planning time data and project cost data, obtaining a prediction result, generating a predictive suggestion according to the prediction result, and optimizing the product manufacturing process according to the predictive suggestion.
Optionally, the acquiring historical BOM change data, project plan time data and project cost data includes:
Acquiring historical product design change data, manufacturing change data and cost change data from an information system or manual data, and taking the historical product design change data, the manufacturing change data and the cost change data as historical BOM change data;
project plan time data and project cost data in the product manufacturing process are obtained from the information system.
Optionally, the performing integrity check on the historical BOM change data to obtain target change data that is successfully checked, includes:
the historical BOM change data are subjected to format unification, repeated values, missing values and abnormal values in the historical BOM change data are subjected to data filtering processing, and processed filtering change data are obtained;
extracting the characteristics of the filtering change data to obtain a characteristic data set;
splitting the characteristic data set into a training data set and a verification data set, training an initial integrity verification model according to a preset clustering algorithm and the training data set, and determining a final model according to the verification data set;
and inputting the filtered change data into the final model for integrity verification to obtain target change data successfully verified.
Optionally, the feature extracting the filtering change data to obtain a feature data set includes:
and obtaining the model type of the current integrity verification model, determining a necessary field according to the model type, extracting the characteristics corresponding to the necessary field from the filtering change data, classifying and collecting the characteristics, and generating a characteristic data set.
Optionally, the inputting the filtered change data to the final model for integrity verification to obtain target change data with successful verification includes:
inputting the filtering change data into the final model to obtain a change component clustering result;
the initial correlation coefficient among all the parts in the change component clustering result is obtained through the following formula:
wherein,for initial correlation coefficient, C ij Cosine is included angle after data standardization, n is the number of variables, i is part i, j is part j, x ti For the value of the t-th variable for part i, < >>To average all variables for part i, x tj For the value of the t-th variable for part j, < >>For the average of all variables for part j +.>The closer to 1, the stronger the correlation between parts ij is shown;
Obtaining the product function code in the filtering change data, and calculating the correlation coefficient after the parts in the same cluster are interacted and checked according to the product function code through the following formula:
wherein p is ij Correlation coefficients after verification for parts in the same cluster,for the initial correlation coefficient, m represents the function code and has m bits, k represents the k bit of the function code, s k 0 or 1, s when the kth function code of the part ij is the same k 1, s when the kth function code of the part ij is different k 0,w of a shape of 0,w k The weight value is the k-th functional code weight value;
and determining target change data successfully verified in the filtered change data according to the verified correlation coefficient.
Optionally, predicting the influence of the target change data on project plan time data and project cost data, obtaining a prediction result, generating a predictive suggestion according to the prediction result, and optimizing a product manufacturing process according to the predictive suggestion, including:
integrating the target change data according to component codes to obtain time difference data of each node in the target change data;
inputting the time difference data into a preset machine learning algorithm to obtain variable data, and predicting the influence of the target change data on project planning time data and project cost data according to the variable data to obtain a prediction result;
And generating predictive suggestions for designing key influence nodes in advance according to the prediction results, and optimizing the product manufacturing process according to the predictive suggestions.
Optionally, the inputting the time difference data into a preset machine learning algorithm to obtain variable data, predicting the influence of the target change data on project planning time data and project cost data according to the variable data, and obtaining a prediction result includes:
obtaining a first time difference variable of a change time and a design completion time, a second time difference variable of the change time and a manufacture start time from the time difference data, a third time difference variable of the change time and a planned trial production time, a fourth time difference variable of the design completion time and the planned trial production time, and a fifth time difference variable of the manufacture start time and the planned trial production time;
inputting the first time difference variable, the second time difference variable, the third time difference variable, the fourth time difference variable and the fifth time difference variable into a preset machine learning algorithm to obtain the plan cost difference before and after the change of each node in the target change data;
And predicting the influence of the target change data on project planning time data and project cost data according to the time difference data and the planning cost difference to obtain a prediction result.
In order to achieve the above object, the present invention further provides a product and manufacturing data intelligent optimization device, which includes:
the data acquisition module is used for acquiring historical BOM change data, project planning time data and project cost data;
the integrity checking module is used for carrying out integrity checking on the historical BOM change data to obtain target change data which is successfully checked;
and the prediction optimization module is used for predicting the influence of the target change data on project planning time data and project cost data, obtaining a prediction result, generating a predictive suggestion according to the prediction result, and optimizing the product manufacturing process according to the predictive suggestion.
In order to achieve the above object, the present invention further provides a product and manufacturing data intelligent optimization device, where the product and manufacturing data intelligent optimization device includes: the system comprises a memory, a processor, and a product and manufacturing data intelligent optimization program stored on the memory and executable on the processor, the product and manufacturing data intelligent optimization program configured to implement the steps of the product and manufacturing data intelligent optimization method as described above.
In a fourth aspect, to achieve the above object, the present invention further proposes a storage medium having stored thereon a product and manufacturing data intelligent optimization program, which when executed by a processor, implements the steps of the product and manufacturing data intelligent optimization method as described above.
According to the intelligent optimization method for the product and the manufacturing data, the historical BOM change data, the project planning time data and the project cost data are obtained; carrying out integrity check on the historical BOM change data to obtain target change data which is successfully checked; predicting the influence of the target change data on project planning time data and project cost data, obtaining a prediction result, generating a predictive suggestion according to the prediction result, and optimizing a product manufacturing process according to the predictive suggestion; the data integrity verification can be carried out, the data change workload and the data change error rate are reduced, the problems of untimely manufacturing and supply, node delay, production line stop and the like caused by incomplete data change are avoided, and the time and cost loss are reduced; the BOM change can be accurately, efficiently and completely carried out, the product inventory can be reduced, the production efficiency is improved, delivery is guaranteed, the cost is reduced, the time of coordination and communication is reduced, and the waste of manpower and material resources is avoided.
Drawings
FIG. 1 is a schematic diagram of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flow chart of a first embodiment of the intelligent optimization method for product and manufacturing data according to the present invention;
FIG. 3 is a flow chart of a second embodiment of the intelligent optimization method for product and manufacturing data according to the present invention;
FIG. 4 is a flow chart of a third embodiment of the intelligent optimization method for product and manufacturing data according to the present invention;
FIG. 5 is a schematic diagram showing the result of the K-means algorithm model in the intelligent optimization method of the product and manufacturing data;
FIG. 6 is a schematic diagram of the comparison of the front and back of the introduction of "function code" verification in the intelligent optimization method of the product and manufacturing data of the present invention;
FIG. 7 is a flow chart of a fourth embodiment of the intelligent optimization method for product and manufacturing data according to the present invention;
FIG. 8 is a schematic flow chart of a fifth embodiment of the intelligent optimization method for product and manufacturing data according to the present invention;
FIG. 9 is a schematic diagram of a case of feature fields predictively maintained in an intelligent optimization method for product and manufacturing data according to the present invention;
FIG. 10 is a schematic diagram of predictive maintenance cases in the intelligent optimization method of product and manufacturing data according to the present invention;
FIG. 11 is a functional block diagram of a first embodiment of the intelligent optimizing apparatus for product and manufacturing data according to the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The solution of the embodiment of the invention mainly comprises the following steps: project planning time data and project cost data are obtained by obtaining historical BOM change data; carrying out integrity check on the historical BOM change data to obtain target change data which is successfully checked; predicting the influence of the target change data on project planning time data and project cost data, obtaining a prediction result, generating a predictive suggestion according to the prediction result, and optimizing a product manufacturing process according to the predictive suggestion; the data integrity verification can be carried out, the data change workload and the data change error rate are reduced, the problems of untimely manufacturing and supply, node delay, production line stop and the like caused by incomplete data change are avoided, and the time and cost loss are reduced; the BOM change can be accurately, efficiently and completely carried out, the product inventory can be reduced, the production efficiency is improved, the delivery is ensured, the cost is reduced, the coordinated communication time is reduced, the waste of manpower and material resources is avoided, the technical problems that in the prior art, the manual checking and writing workload is large, errors are easy to occur in the process of processing the product and manufacturing data, the economic loss caused by inconsistent final products is easy to cause when the product design is changed, the data change error rate is high, the influence of the data change on project time and cost is large, and the data value is easy to lose are solved.
Referring to fig. 1, fig. 1 is a schematic device structure diagram of a hardware running environment according to an embodiment of the present invention.
As shown in fig. 1, the apparatus may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., wi-Fi interface). The Memory 1005 may be a high-speed RAM Memory or a stable Memory (Non-Volatile Memory), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the apparatus structure shown in fig. 1 is not limiting of the apparatus and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
As shown in fig. 1, an operating device, a network communication module, a user interface module, and an intelligent optimization program for product and manufacturing data may be included in the memory 1005 as one type of storage medium.
The apparatus of the present invention calls the product and manufacturing data intelligent optimization program stored in the memory 1005 through the processor 1001 and performs the following operations:
acquiring historical BOM change data, project planning time data and project cost data;
carrying out integrity check on the historical BOM change data to obtain target change data which is successfully checked;
predicting the influence of the target change data on project planning time data and project cost data, obtaining a prediction result, generating a predictive suggestion according to the prediction result, and optimizing the product manufacturing process according to the predictive suggestion.
The apparatus of the present invention calls the product and manufacturing data intelligent optimization program stored in the memory 1005 through the processor 1001, and also performs the following operations:
acquiring historical product design change data, manufacturing change data and cost change data from an information system or manual data, and taking the historical product design change data, the manufacturing change data and the cost change data as historical BOM change data;
project plan time data and project cost data in the product manufacturing process are obtained from the information system.
The apparatus of the present invention calls the product and manufacturing data intelligent optimization program stored in the memory 1005 through the processor 1001, and also performs the following operations:
The historical BOM change data are subjected to format unification, repeated values, missing values and abnormal values in the historical BOM change data are subjected to data filtering processing, and processed filtering change data are obtained;
extracting the characteristics of the filtering change data to obtain a characteristic data set;
splitting the characteristic data set into a training data set and a verification data set, training an initial integrity verification model according to a preset clustering algorithm and the training data set, and determining a final model according to the verification data set;
and inputting the filtered change data into the final model for integrity verification to obtain target change data successfully verified.
The apparatus of the present invention calls the product and manufacturing data intelligent optimization program stored in the memory 1005 through the processor 1001, and also performs the following operations:
and obtaining the model type of the current integrity verification model, determining a necessary field according to the model type, extracting the characteristics corresponding to the necessary field from the filtering change data, classifying and collecting the characteristics, and generating a characteristic data set.
The apparatus of the present invention calls the product and manufacturing data intelligent optimization program stored in the memory 1005 through the processor 1001, and also performs the following operations:
Inputting the filtering change data into the final model to obtain a change component clustering result;
the initial correlation coefficient among all the parts in the change component clustering result is obtained through the following formula:
wherein,for initial correlation coefficient, C ij Cosine is included angle after data standardization, n is the number of variables, i is part i, j is part j, x ti For the value of the t-th variable for part i, < >>To average all variables for part i, x tj For the value of the t-th variable for part j, < >>For the average of all variables for part j +.>The closer to 1, the stronger the correlation between parts ij is shown;
obtaining the product function code in the filtering change data, and calculating the correlation coefficient after the parts in the same cluster are interacted and checked according to the product function code through the following formula:
wherein p is ij Correlation coefficients after verification for parts in the same cluster,for the initial correlation coefficient, m represents the function code and has m bits, k represents the k bit of the function code, s k 0 or 1, s when the kth function code of the part ij is the same k 1, s when the kth function code of the part ij is different k 0,w of a shape of 0,w k The weight value is the k-th functional code weight value;
and determining target change data successfully verified in the filtered change data according to the verified correlation coefficient.
The apparatus of the present invention calls the product and manufacturing data intelligent optimization program stored in the memory 1005 through the processor 1001, and also performs the following operations:
integrating the target change data according to component codes to obtain time difference data of each node in the target change data;
inputting the time difference data into a preset machine learning algorithm to obtain variable data, and predicting the influence of the target change data on project planning time data and project cost data according to the variable data to obtain a prediction result;
and generating predictive suggestions for designing key influence nodes in advance according to the prediction results, and optimizing the product manufacturing process according to the predictive suggestions.
The apparatus of the present invention calls the product and manufacturing data intelligent optimization program stored in the memory 1005 through the processor 1001, and also performs the following operations:
obtaining a first time difference variable of a change time and a design completion time, a second time difference variable of the change time and a manufacture start time from the time difference data, a third time difference variable of the change time and a planned trial production time, a fourth time difference variable of the design completion time and the planned trial production time, and a fifth time difference variable of the manufacture start time and the planned trial production time;
Inputting the first time difference variable, the second time difference variable, the third time difference variable, the fourth time difference variable and the fifth time difference variable into a preset machine learning algorithm to obtain the plan cost difference before and after the change of each node in the target change data;
and predicting the influence of the target change data on project planning time data and project cost data according to the time difference data and the planning cost difference to obtain a prediction result.
According to the scheme, the project planning time data and the project cost data are obtained through the historical BOM change data; carrying out integrity check on the historical BOM change data to obtain target change data which is successfully checked; predicting the influence of the target change data on project planning time data and project cost data, obtaining a prediction result, generating a predictive suggestion according to the prediction result, and optimizing a product manufacturing process according to the predictive suggestion; the data integrity verification can be carried out, the data change workload and the data change error rate are reduced, the problems of untimely manufacturing and supply, node delay, production line stop and the like caused by incomplete data change are avoided, and the time and cost loss are reduced; the BOM change can be accurately, efficiently and completely carried out, the product inventory can be reduced, the production efficiency is improved, delivery is guaranteed, the cost is reduced, the time of coordination and communication is reduced, and the waste of manpower and material resources is avoided.
Based on the hardware structure, the embodiment of the intelligent optimization method for the product and the manufacturing data is provided.
Referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the intelligent optimization method for product and manufacturing data according to the present invention.
In a first embodiment, the intelligent optimization method for the product and manufacturing data comprises the following steps:
step S10, acquiring historical BOM change data, project planning time data and project cost data.
The BOM change data is corresponding data generated by bill of materials change, and the project plan time data is data corresponding to each project plan time and project cost related data.
And step S20, carrying out integrity check on the historical BOM change data to obtain target change data which is successfully checked.
It can be appreciated that the integrity of the historical BOM change data is checked, so that the target change data with successful verification can be obtained.
And step S30, predicting the influence of the target change data on project planning time data and project cost data, obtaining a prediction result, generating a predictive suggestion according to the prediction result, and optimizing the product manufacturing process according to the predictive suggestion.
It should be understood that, the influence of the target change data on the project plan time data and the project cost data, that is, the influence of the change part on the project plan time and the project cost, is predicted, so as to obtain a prediction result, and further, a predictive suggestion may be generated according to the prediction result, for example, a prompt may be deployed in advance for a corresponding project node, or the design time of the corresponding project node may be advanced, or some redundant project nodes may be eliminated, or the cost of some project nodes may be reduced.
According to the scheme, the project planning time data and the project cost data are obtained through the historical BOM change data; carrying out integrity check on the historical BOM change data to obtain target change data which is successfully checked; predicting the influence of the target change data on project planning time data and project cost data, obtaining a prediction result, generating a predictive suggestion according to the prediction result, and optimizing a product manufacturing process according to the predictive suggestion; the data integrity verification can be carried out, the data change workload and the data change error rate are reduced, the problems of untimely manufacturing and supply, node delay, production line stop and the like caused by incomplete data change are avoided, and the time and cost loss are reduced; the BOM change can be accurately, efficiently and completely carried out, the product inventory can be reduced, the production efficiency is improved, delivery is guaranteed, the cost is reduced, the time of coordination and communication is reduced, and the waste of manpower and material resources is avoided.
Further, fig. 3 is a schematic flow chart of a second embodiment of the product and manufacturing data intelligent optimization method according to the present invention, as shown in fig. 3, according to the second embodiment of the product and manufacturing data intelligent optimization method according to the present invention, in this embodiment, the step S10 specifically includes the following steps:
step S11, historical product design change data, manufacturing change data and cost change data are obtained from an information system or manual data, and the historical product design change data, the manufacturing change data and the cost change data are used as historical BOM change data.
The historical product design change data, the manufacturing change data, and the cost change data may be acquired from an information system or manual data, and the historical product design change data, the manufacturing change data, and the cost change data may be used as historical BOM change data.
In particular implementations, the historical BOM change dataset (change notice/change data sheet) may be obtained from a system or manual data, where the system refers to various information systems such as product lifecycle management (Product Lifecycle Management, PLM), enterprise resource planning (Enterprise Resource Planning, ERP), advanced planning and scheduling (Advanced Planning and Scheduling, APS), manufacturing execution systems (Manufacturing Execution System, MES), and the like.
Step S12, project plan time data and project cost data in the product manufacturing process are obtained from the information system.
It will be appreciated that project plan time data and project cost data for the plan and actual node times in the product manufacturing process may be obtained from the information system.
According to the scheme, historical product design change data, manufacturing change data and cost change data are obtained from an information system or manual data, and the historical product design change data, the manufacturing change data and the cost change data are used as historical BOM change data; project planning time data and project cost data in the product manufacturing process are obtained from the information system, historical BOM change data and project planning time data and project cost data can be accurately obtained, data change workload and data change error rate are reduced, and intelligent optimization efficiency of the product and manufacturing data is improved.
Further, fig. 4 is a schematic flow chart of a third embodiment of the intelligent optimization method for product and manufacturing data according to the present invention, and as shown in fig. 4, the third embodiment of the intelligent optimization method for product and manufacturing data according to the present invention is proposed based on the first embodiment, and in this embodiment, the step S20 specifically includes the following steps:
And S21, unifying formats of the historical BOM change data, and performing data filtering processing on repeated values, missing values and abnormal values in the historical BOM change data to obtain processed filtering change data.
After the format of the historical BOM change data is unified, the repeated value, the missing value and the abnormal value in the historical BOM change data may be subjected to data filtering processing, so as to obtain the processed filtered change data.
In a specific implementation, the above data in a uniform csv format may be generally imported into an algorithm program to perform repeated value, missing value and outlier data processing, and since these data are used in industrial information systems for different purposes and developed by different suppliers and ages, the derived data field formats are different, and normalization/standardization processing is required.
And S22, extracting the characteristics of the filtering change data to obtain a characteristic data set.
It should be appreciated that the feature engineering is used to extract and select the feature field, and feature extraction may be performed on the filtered change data to obtain a feature data set.
And S23, splitting the characteristic data set into a training data set and a verification data set, training an initial integrity verification model according to a preset clustering algorithm and the training data set, and determining a final model according to the verification data set.
It can be understood that the above data are split into a training data set and a verification data set, a proper algorithm is selected to train the model, namely, the feature data set is split into the training data set and the verification data set, the initial integrity verification model is trained according to a preset clustering algorithm and the training data set, and a final model is determined according to the verification data set.
It should be appreciated that the final model may be obtained by evaluating the trained model, changing model parameters, improving feature engineering, and improving model accuracy.
In a specific implementation, the K-Means algorithm may be taken as an example: for a given change dataset D, partitioning D into K subsets requires that the degree of dissimilarity between elements within each subset be as low as possible, i.e., the likelihood of components changing simultaneously within the same subset is greatest.
1. Points in K feature spaces are randomly set as initial cluster centers.
2. The following procedure was repeated until the cluster center was no longer changed:
a. for each cluster C 1 ,C 2 …C k Determining an initial cluster center
b. And distributing the samples in the sample set to the nearest clusters according to a minimum distance principle.
c. Using the sample mean in each cluster as a new cluster center
3. The clustering effect is measured using the square error (Sum of Squared Error, SSE) to determine the appropriate K value.
Wherein x is (j) Is C i Sample points, mu (i) Is C i Centroid (C) i Average of all samples in (a)
4. And outputting the final cluster center and the category to which each sample belongs.
And step S24, inputting the filtered change data into the final model for integrity verification, and obtaining target change data which is successfully verified.
It can be understood that the new change data is input into the optimal model, that is, the filtered change data is input into the final model for integrity verification, so as to obtain target change data with successful verification.
Further, the step S24 specifically includes the following steps:
inputting the filtering change data into the final model to obtain a change component clustering result;
the initial correlation coefficient among all the parts in the change component clustering result is obtained through the following formula:
wherein,for initial correlation coefficient, C ij Cosine is included angle after data standardization, n is the number of variables, i is part i, j is part j, x ti For the value of the t-th variable for part i, < >>To average all variables for part i, x tj For the value of the t-th variable for part j, < >>For the average of all variables for part j +.>The closer to 1, the stronger the correlation between parts ij is shown;
obtaining the product function code in the filtering change data, and calculating the correlation coefficient after the parts in the same cluster are interacted and checked according to the product function code through the following formula:
wherein p is ij Correlation coefficients after verification for parts in the same cluster,for the initial correlation coefficient, m represents the function code and has m bits, k represents the k bit of the function code, s k 0 or 1, s when the kth function code of the part ij is the same k 1, s when the kth function code of the part ij is different k 0,w of a shape of 0,w k The weight value is the k-th functional code weight value;
and determining target change data successfully verified in the filtered change data according to the verified correlation coefficient.
In a specific implementation, new change data are input into an optimal model, a change component clustering result is fed back, the possibility that components in the same cluster are changed together is high, as shown in fig. 5, fig. 5 is a visual display schematic diagram of a K-means algorithm model result in the product and manufacturing data intelligent optimization method, and referring to fig. 5, namely, the change of a part 1 in the same cluster is likely to be accompanied with the change of a part 2 and a part 3 in the same cluster, the possibility that a part 4 in another cluster is changed is low, and part change correlation sorting can provide a reference for complete verification of subsequent changes.
The correlation coefficient is used for representing the correlation between parts, and thermodynamic diagrams can be used for visual display; the larger the similarity coefficient, the smaller the distance, when 1, the distance is 0, C ij The method is characterized in that the cosine of the included angle is obtained after data is standardized, and the accuracy of the integrity verification result can be improved by utilizing the function code.
And further calculating the parts in the same cluster by calculating the obtained correlation coefficient.
For an n-bit function, each bit is compared, and if the k of the function codes of two parts ij are equal, s is 1, and the coefficient w is multiplied k And after summation, calculating to obtain a correlation coefficient p after verification. For p greater than threshold p t As a final output.
As shown in fig. 6, fig. 6 is a schematic diagram showing the comparison of the front and back of the "function code" verification introduced in the intelligent optimization method for product and manufacturing data according to the present invention, and referring to fig. 6, when the "function code" verification is not cited, the probability of setting the part a to be changed along with the setting of the fastener B and the fastener B 'is greater than that of setting the part C, and the fastener B' have the same part number, but the positions and functions are different.
According to the scheme, the format of the historical BOM change data is unified, and the repeated value, the missing value and the abnormal value in the historical BOM change data are subjected to data filtering processing to obtain processed filtering change data; extracting the characteristics of the filtering change data to obtain a characteristic data set; splitting the characteristic data set into a training data set and a verification data set, training an initial integrity verification model according to a preset clustering algorithm and the training data set, and determining a final model according to the verification data set; the filtering change data is input into the final model for integrity verification, so that target change data with successful verification is obtained, data integrity verification can be performed, data change workload and data change error rate are reduced, the problems of untimely manufacturing supply, node delay, production line stop and the like caused by incomplete data change are avoided, and time and cost losses are reduced.
Further, fig. 7 is a schematic flow chart of a fourth embodiment of the intelligent optimization method for product and manufacturing data according to the present invention, as shown in fig. 7, according to a third embodiment of the present invention, the step S22 specifically includes the following steps:
step S221, obtaining the model type of the current integrity verification model, determining a necessary field according to the model type, extracting the characteristics corresponding to the necessary field from the filtering change data, classifying and collecting the characteristics, and generating a characteristic data set.
The method includes that model types of different integrity verification models correspond to different necessary fields, and further features corresponding to the necessary fields can be extracted from the filtering change data, and the features are classified and collected to generate a feature data set.
In a specific implementation, if the current integrity verification model is used for verifying the integrity of the EBOM change data of the product design, the change reason, the change mark (change of the number), the component code, the function code, the designer/department, the vehicle type grade and the manufacturing route are necessary fields; meanwhile, a new field can be created, for example, the distance between the change time and the time of each node of the project is calculated, and the parts changed in the same batch are marked; screening out unique characteristic fields such as digital-analog drawing numbers, change notice numbers and the like.
If the model is used for verifying the integrity of the MBOM change data, the number of parts, the information of the parts along, the information of suppliers and the assembly route are necessary fields except the characteristic fields; meanwhile, the distances between the manufacturing start/stop time, the changing time and the project node time of different versions of the same part are calculated, the configuration expression of the part trailer relationship is reflected, and the part trailer relationship also needs to be split into a plurality of items.
If the model is used for verifying the integrity of the process PBOM change data, material information, process routes, assembly relations, assembly quantity and process codes are necessary fields except the characteristic fields.
For sales SBOM changes, vendor change information, recall part information, etc. fields are necessary fields.
In addition, the numerical type characteristic field is added to construct the statistical characteristics of quartiles, medians, average values, standard deviations, deviations and the like; data from time distances, statistics of longer periods such as weeks and months are characterized; and carrying out mathematical transformation, combination and splitting of the characteristic fields according to the service requirements.
According to the scheme, the necessary fields are determined according to the model types by acquiring the model types of the current integrity verification model, the characteristics corresponding to the necessary fields are extracted from the filtering change data, the characteristics are classified and collected, and the characteristic data set is generated, so that the corresponding characteristic data can be obtained, the data change workload and the data change error rate are reduced, the problems of untimely manufacturing supply, node delay, production line stop and the like caused by incomplete data change are avoided, and the time and cost loss are reduced.
Further, fig. 8 is a schematic flow chart of a fifth embodiment of the intelligent optimization method for product and manufacturing data according to the present invention, as shown in fig. 8, according to the fifth embodiment of the intelligent optimization method for product and manufacturing data according to the present invention is proposed based on the first embodiment, in which the step S30 specifically includes the following steps:
and S31, integrating the target change data according to the component codes to obtain time difference data of each node in the target change data.
It should be appreciated that from the system or manual data, historical product design EBOM, manufacturing MBOM, and cost CBOM change datasets (change notifications/change data tables) are obtained; the system herein refers to PLM (product lifecycle management), ERP (Enterprise resource planning), APS (advanced planning and scheduling), MES (manufacturing execution System), and other different information systems.
It can be understood that, at the same time, the plan and actual node time and cost data are acquired; importing the data into an algorithm program in a csv format; performing repeated value, missing value and abnormal value data processing; since these data are used in industrial information systems for different purposes, developed by different suppliers, years, the derived data field formats are all different, requiring normalization/normalization processing; the special parts of each vehicle type can be removed, or the historical data of similar vehicle types can be selected as input data, so that the accuracy is improved; and integrating the change data according to the component codes, extracting and selecting the characteristic fields by utilizing the characteristic engineering, and obtaining the time difference data of each node in the target change data.
It should be understood that the feature field includes: change cause, change mark (change of number), component code, function code, designer/department, vehicle model class, manufacturing route, part number, piece information, supplier information, assembly route; screening out unique characteristic fields such as a digital-analog drawing number, a change notice number and the like; the configuration expression for representing the part trailer relationship also needs to be split into a plurality of items; meanwhile, new fields can be created, such as calculating the distance between the design change time and the project node time, and the distance between the manufacturing start/stop time and the change time and the project node time; in addition, the numerical type characteristic field is added to construct the statistical characteristics of quartiles, medians, average values, standard deviations, deviations and the like; data from time distances, statistics of longer periods such as weeks and months are characterized; and carrying out mathematical transformation, combination and splitting of the characteristic fields according to the service requirements.
In a specific implementation, as shown in fig. 9, fig. 9 is a schematic diagram of a feature field case of predictive maintenance in the intelligent optimization method of product and manufacturing data according to the present invention, referring to fig. 9, it is assumed that for a certain component, 3 design changes are performed before planning node a, and each design change estimates a manufacturing change start time, which means that a newly designed component/part is manufactured from this time; according to the rule, the final design needs to be completed before planning node a, and planning node b starts manufacturing; the design change of the previous two times is used for estimating the coincidence of the initial time points of the manufacturing change 1 and the manufacturing change 2; but the 3 rd design change is too close to planning node a, causing the vendor to produce the final product of design change 3 less quickly, delaying the start time of manufacturing change 3; resulting in the actual node b occurring later than the planned time. The above change information can be integrated into 3 pieces of data, with the following feature fields added:
Time difference between planned node, actual node and 3 design changes
Time difference between actual node and 3 manufacturing changes
Design/manufacturing variation time differences between different versions
If the model is used for predicting the influence of the changed part on project planning time, the tag term can be the difference between the actual and planning time of the important node; if the model is to predict the impact of changing parts on project costs, the tag term may be a significant node with poor planning costs before and after the change.
In the case of predicting the influence of 3 "antenna group" part design changes on the time plan of a trial run, a plurality of time differences (in days) may be calculated as the newly added feature field, and the node delay as the label.
The data are split into a training data set and a verification data set, a proper algorithm is selected to train the model, model parameters are changed, feature engineering is improved, model accuracy is improved, the verification data set is utilized to enable the model to predict results, and model accuracy is evaluated.
And S32, inputting the time difference data into a preset machine learning algorithm to obtain variable data, and predicting the influence of the target change data on project planning time data and project cost data according to the variable data to obtain a prediction result.
It can be understood that the time difference data is input to a preset machine learning algorithm, variable data can be obtained, and then the influence of the target change data on project planning time data and project cost data is predicted according to the variable data, so as to obtain a prediction result.
Further, the step S32 specifically includes the following steps:
obtaining a first time difference variable of a change time and a design completion time, a second time difference variable of the change time and a manufacture start time from the time difference data, a third time difference variable of the change time and a planned trial production time, a fourth time difference variable of the design completion time and the planned trial production time, and a fifth time difference variable of the manufacture start time and the planned trial production time;
inputting the first time difference variable, the second time difference variable, the third time difference variable, the fourth time difference variable and the fifth time difference variable into a preset machine learning algorithm to obtain the plan cost difference before and after the change of each node in the target change data;
and predicting the influence of the target change data on project planning time data and project cost data according to the time difference data and the planning cost difference to obtain a prediction result.
It should be understood that a first time difference variable of a change time and a design completion time, a second time difference variable of the change time and a manufacturing start time, a third time difference variable of the change time and a planned trial production time, a fourth time difference variable of the design completion time and the planned trial production time, and a fifth time difference variable of the manufacturing start time and the planned trial production time are obtained from the time difference data; the first time difference variable, the second time difference variable, the third time difference variable, the fourth time difference variable and the fifth time difference variable can be input into a preset machine learning algorithm to obtain the plan cost difference before and after the change of each node in the target change data, and obtain the plan cost difference before and after the change of each node in the target change data; and predicting the influence of the target change data on project planning time data and project cost data according to the time difference data and the planning cost difference to obtain a prediction result.
In a specific implementation, the algorithm model may employ linear Regression (Linear Regression), ridge Regression (Ridge Regression), lasso Regression, support vector Regression, decision tree Regression, XGBoost, lightGBM, catBoost, and the like; linear regression, ridge regression, lasso regression, support vector regression, decision tree regression, are traditional machine learning algorithms, and are inferior to integrated learning algorithms in accuracy and performance. XGBoost, lightGBM, catBoost as the most advanced modern integrated learning algorithm can be well applied to the multi-dimensional complex feature input of the patent; XGBoost training time is too long, lightGBM improves efficiency, accuracy is low, catoost well balances advantages of two algorithms, and the XGBoost training method is the most applicable algorithm model at the present stage.
It can be understood that, referring to fig. 10, fig. 10 is a schematic diagram of a predictive maintenance case in the intelligent optimization method of product and manufacturing data according to the present invention, referring to fig. 10, new modification data is input into a Catboost algorithm model, analysis results of contributions to related variables are fed back, and data time plan and cost impact prediction are fed back; as shown in fig. 10, in the case of predicting the influence of the model on a certain node by analyzing the historical data, the influence of the change of the obtained part 2 on the time and the cost is relatively large, so that the design of the part 2 should be determined in advance, and the delay of the design change should be avoided as much as possible.
It should be understood that, in this embodiment, by using a machine learning algorithm, by analyzing the influence of historical products and manufacturing change data on time and cost, a predictive suggestion is provided for the influence caused by part change in the future, so that the conditions of node delay and cost increase caused by change are reduced, the accuracy of project decision is improved, the risk is controlled quantitatively, and the product competitiveness is improved; the embodiment can also be used as an independent module and applied to BOM management systems such as PDM, ERP, PLM or application systems, so that industrial big data value is mined, personalized management scheme promotion is provided for enterprises, and processing efficiency of intelligent system modification, query and other operations is improved.
And step S33, generating a predictive suggestion for designing key influence nodes in advance according to the prediction result, and optimizing the product manufacturing process according to the predictive suggestion.
It should be understood that, generating predictive advice for designing important influence nodes in advance according to the prediction result, and optimizing the product manufacturing process according to the predictive advice; generating a predictive suggestion according to the prediction result, for example, performing early deployment reminding on the corresponding project node, or advancing the design time of the corresponding project node, or eliminating some redundant project nodes, or reducing the cost of some project nodes, etc., which is not limited in this embodiment, and optimizing the product manufacturing process according to the predictive suggestion.
According to the scheme, the target change data are integrated according to the component codes, so that time difference data of each node in the target change data are obtained; inputting the time difference data into a preset machine learning algorithm to obtain variable data, and predicting the influence of the target change data on project planning time data and project cost data according to the variable data to obtain a prediction result; generating predictive suggestions for influencing the nodes in advance according to the prediction results, optimizing the product manufacturing process according to the predictive suggestions, and performing data integrity verification, so that the data change workload and the data change error rate are reduced, the problems of untimely manufacturing supply, node delay, production line stop and the like caused by incomplete data change are avoided, and the time and cost loss is reduced; the BOM change can be accurately, efficiently and completely carried out, the product inventory can be reduced, the production efficiency is improved, delivery is guaranteed, the cost is reduced, the time of coordination and communication is reduced, and the waste of manpower and material resources is avoided.
Correspondingly, the invention further provides a product and manufacturing data intelligent optimization device.
Referring to fig. 11, fig. 11 is a functional block diagram of a first embodiment of the intelligent optimizing apparatus for product and manufacturing data according to the present invention.
In a first embodiment of the product and manufacturing data intelligent optimization apparatus of the present invention, the product and manufacturing data intelligent optimization apparatus includes:
the data acquisition module 10 is used for acquiring historical BOM change data, project planning time data and project cost data.
And the integrity checking module 20 is configured to perform integrity checking on the historical BOM change data, so as to obtain target change data that is successfully checked.
The prediction optimization module 30 is configured to predict an influence of the target change data on project planning time data and project cost data, obtain a prediction result, generate a predictive suggestion according to the prediction result, and optimize a product manufacturing process according to the predictive suggestion.
The data acquisition module 10 is further configured to acquire historical product design change data, manufacturing change data, and cost change data from an information system or manual data, and take the historical product design change data, the manufacturing change data, and the cost change data as historical BOM change data; project plan time data and project cost data in the product manufacturing process are obtained from the information system.
The integrity verification module 20 is further configured to perform format unification on the historical BOM change data, perform data filtering processing on the repeated value, the missing value and the abnormal value in the historical BOM change data, and obtain processed filtered change data; extracting the characteristics of the filtering change data to obtain a characteristic data set; splitting the characteristic data set into a training data set and a verification data set, training an initial integrity verification model according to a preset clustering algorithm and the training data set, and determining a final model according to the verification data set; and inputting the filtered change data into the final model for integrity verification to obtain target change data successfully verified.
The integrity verification module 20 is further configured to obtain a model type of a current integrity verification model, determine a necessary field according to the model type, extract a feature corresponding to the necessary field from the filtered change data, classify the feature, and generate a feature dataset.
The integrity verification module 20 is further configured to input the filtered modification data to the final model, to obtain a modification component clustering result;
The initial correlation coefficient among all the parts in the change component clustering result is obtained through the following formula:
wherein,for initial correlation coefficient, C ij Cosine is included angle after data standardization, n is the number of variables, i is part i, j is part j, x ti For the value of the t-th variable for part i, < >>To average all variables for part i, x tj For the value of the t-th variable for part j, < >>For the average of all variables for part j +.>The closer to 1, the stronger the correlation between parts ij is shown;
obtaining the product function code in the filtering change data, and calculating the correlation coefficient after the parts in the same cluster are interacted and checked according to the product function code through the following formula:
wherein p is ij Correlation coefficients after verification for parts in the same cluster,for the initial correlation coefficient, m represents the function code and has m bits, k represents the k bit of the function code, s k 0 or 1, s when the kth function code of the part ij is the same k 1, s when the kth function code of the part ij is different k 0,w of a shape of 0,w k The weight value is the k-th functional code weight value;
and determining target change data successfully verified in the filtered change data according to the verified correlation coefficient.
The prediction optimization module 30 is further configured to integrate the target change data according to component encoding, so as to obtain time difference data of each node in the target change data; inputting the time difference data into a preset machine learning algorithm to obtain variable data, and predicting the influence of the target change data on project planning time data and project cost data according to the variable data to obtain a prediction result; and generating predictive suggestions for designing key influence nodes in advance according to the prediction results, and optimizing the product manufacturing process according to the predictive suggestions.
The prediction optimization module 30 is further configured to obtain, from the time difference data, a first time difference variable between a change time and a design completion time, a second time difference variable between the change time and a manufacturing start time, a third time difference variable between the change time and a planned trial production time, a fourth time difference variable between the design completion time and the planned trial production time, and a fifth time difference variable between the manufacturing start time and the planned trial production time; inputting the first time difference variable, the second time difference variable, the third time difference variable, the fourth time difference variable and the fifth time difference variable into a preset machine learning algorithm to obtain the plan cost difference before and after the change of each node in the target change data; and predicting the influence of the target change data on project planning time data and project cost data according to the time difference data and the planning cost difference to obtain a prediction result.
The steps for implementing each functional module of the product and manufacturing data intelligent optimization device can refer to each embodiment of the product and manufacturing data intelligent optimization method of the present invention, and will not be described herein.
In addition, the embodiment of the invention also provides a storage medium, wherein the storage medium stores a product and manufacturing data intelligent optimization program, and the product and manufacturing data intelligent optimization program realizes the following operations when being executed by a processor:
acquiring historical BOM change data, project planning time data and project cost data;
carrying out integrity check on the historical BOM change data to obtain target change data which is successfully checked;
predicting the influence of the target change data on project planning time data and project cost data, obtaining a prediction result, generating a predictive suggestion according to the prediction result, and optimizing the product manufacturing process according to the predictive suggestion.
Further, the product and manufacturing data intelligent optimization program, when executed by the processor, further performs the following operations:
acquiring historical product design change data, manufacturing change data and cost change data from an information system or manual data, and taking the historical product design change data, the manufacturing change data and the cost change data as historical BOM change data;
Project plan time data and project cost data in the product manufacturing process are obtained from the information system.
Further, the product and manufacturing data intelligent optimization program, when executed by the processor, further performs the following operations:
the historical BOM change data are subjected to format unification, repeated values, missing values and abnormal values in the historical BOM change data are subjected to data filtering processing, and processed filtering change data are obtained;
extracting the characteristics of the filtering change data to obtain a characteristic data set;
splitting the characteristic data set into a training data set and a verification data set, training an initial integrity verification model according to a preset clustering algorithm and the training data set, and determining a final model according to the verification data set;
and inputting the filtered change data into the final model for integrity verification to obtain target change data successfully verified.
Further, the product and manufacturing data intelligent optimization program, when executed by the processor, further performs the following operations:
and obtaining the model type of the current integrity verification model, determining a necessary field according to the model type, extracting the characteristics corresponding to the necessary field from the filtering change data, classifying and collecting the characteristics, and generating a characteristic data set.
Further, the product and manufacturing data intelligent optimization program, when executed by the processor, further performs the following operations:
inputting the filtering change data into the final model to obtain a change component clustering result;
the initial correlation coefficient among all the parts in the change component clustering result is obtained through the following formula:
wherein,for initial correlation coefficient, C ij Cosine is included angle after data standardization, n is the number of variables, i is part i, j is part j, x ti For the value of the t-th variable for part i, < >>To average all variables for part i, x tj For the value of the t-th variable for part j, < >>For the average of all variables for part j +.>Beyond jointNear 1, the stronger the correlation between parts ij;
obtaining the product function code in the filtering change data, and calculating the correlation coefficient after the parts in the same cluster are interacted and checked according to the product function code through the following formula:
wherein p is ij Correlation coefficients after verification for parts in the same cluster,for the initial correlation coefficient, m represents the function code and has m bits, k represents the k bit of the function code, s k 0 or 1, s when the kth function code of the part ij is the same k 1, s when the kth function code of the part ij is different k 0,w of a shape of 0,w k The weight value is the k-th functional code weight value;
and determining target change data successfully verified in the filtered change data according to the verified correlation coefficient.
Further, the product and manufacturing data intelligent optimization program, when executed by the processor, further performs the following operations:
integrating the target change data according to component codes to obtain time difference data of each node in the target change data;
inputting the time difference data into a preset machine learning algorithm to obtain variable data, and predicting the influence of the target change data on project planning time data and project cost data according to the variable data to obtain a prediction result;
and generating predictive suggestions for designing key influence nodes in advance according to the prediction results, and optimizing the product manufacturing process according to the predictive suggestions.
Further, the product and manufacturing data intelligent optimization program, when executed by the processor, further performs the following operations:
obtaining a first time difference variable of a change time and a design completion time, a second time difference variable of the change time and a manufacture start time from the time difference data, a third time difference variable of the change time and a planned trial production time, a fourth time difference variable of the design completion time and the planned trial production time, and a fifth time difference variable of the manufacture start time and the planned trial production time;
Inputting the first time difference variable, the second time difference variable, the third time difference variable, the fourth time difference variable and the fifth time difference variable into a preset machine learning algorithm to obtain the plan cost difference before and after the change of each node in the target change data;
and predicting the influence of the target change data on project planning time data and project cost data according to the time difference data and the planning cost difference to obtain a prediction result.
Those skilled in the art will appreciate that all or part of the steps in implementing the methods of the embodiments described above may be implemented by a program stored in a storage medium, where the program includes several instructions for causing a device (which may be a single-chip microcomputer, a chip or the like) or a processor (processor) to perform all or part of the steps of the methods of the embodiments described herein; and the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. The intelligent optimization method for the product and the manufacturing data is characterized by comprising the following steps of:
acquiring historical BOM change data, project planning time data and project cost data;
carrying out integrity check on the historical BOM change data to obtain target change data which is successfully checked;
predicting the influence of the target change data on project planning time data and project cost data, obtaining a prediction result, generating a predictive suggestion according to the prediction result, and optimizing the product manufacturing process according to the predictive suggestion.
2. The intelligent optimization method for product and manufacturing data according to claim 1, wherein the obtaining historical BOM change data, project plan time data and project cost data comprises:
Acquiring historical product design change data, manufacturing change data and cost change data from an information system or manual data, and taking the historical product design change data, the manufacturing change data and the cost change data as historical BOM change data;
project plan time data and project cost data in the product manufacturing process are obtained from the information system.
3. The intelligent optimization method for product and manufacturing data according to claim 1, wherein the performing integrity check on the historical BOM change data to obtain target change data with successful verification comprises:
the historical BOM change data are subjected to format unification, repeated values, missing values and abnormal values in the historical BOM change data are subjected to data filtering processing, and processed filtering change data are obtained;
extracting the characteristics of the filtering change data to obtain a characteristic data set;
splitting the characteristic data set into a training data set and a verification data set, training an initial integrity verification model according to a preset clustering algorithm and the training data set, and determining a final model according to the verification data set;
and inputting the filtered change data into the final model for integrity verification to obtain target change data successfully verified.
4. The intelligent optimization method of product and manufacturing data according to claim 3, wherein the feature extraction of the filtering modification data to obtain a feature data set comprises:
and obtaining the model type of the current integrity verification model, determining a necessary field according to the model type, extracting the characteristics corresponding to the necessary field from the filtering change data, classifying and collecting the characteristics, and generating a characteristic data set.
5. The intelligent optimization method for product and manufacturing data according to claim 3, wherein the inputting the filtered change data into the final model for integrity verification to obtain the target change data with successful verification comprises:
inputting the filtering change data into the final model to obtain a change component clustering result;
the initial correlation coefficient among all the parts in the change component clustering result is obtained through the following formula:
wherein,for initial correlation coefficient, C ij Cosine is included angle after data standardization, n is the number of variables, i is part i, j is part j, x ti For the value of the t-th variable for part i, < >>To average all variables for part i, x tj For the value of the t-th variable for part j, < >>For the average of all variables for part j +.>The closer to 1, the stronger the correlation between parts ij is shown;
obtaining the product function code in the filtering change data, and calculating the correlation coefficient after the parts in the same cluster are interacted and checked according to the product function code through the following formula:
wherein p is ij Correlation coefficients after verification for parts in the same cluster,for the initial correlation coefficient, m represents the function code and has m bits, k represents the k bit of the function code, s k 0 or 1, when part ij is at the kth positionWhen the function codes are the same, s k 1, s when the kth function code of the part ij is different k 0,w of a shape of 0,w k The weight value is the k-th functional code weight value;
and determining target change data successfully verified in the filtered change data according to the verified correlation coefficient.
6. The intelligent optimization method of product and manufacturing data according to claim 1, wherein predicting the influence of the target change data on project planning time data and project cost data, obtaining a prediction result, generating a predictive suggestion according to the prediction result, and optimizing a product manufacturing process according to the predictive suggestion, comprises:
Integrating the target change data according to component codes to obtain time difference data of each node in the target change data;
inputting the time difference data into a preset machine learning algorithm to obtain variable data, and predicting the influence of the target change data on project planning time data and project cost data according to the variable data to obtain a prediction result;
and generating predictive suggestions for designing key influence nodes in advance according to the prediction results, and optimizing the product manufacturing process according to the predictive suggestions.
7. The intelligent optimization method of product and manufacturing data according to claim 6, wherein the inputting the time difference data into a preset machine learning algorithm to obtain variable data, predicting the influence of the target change data on project planning time data and project cost data according to the variable data, and obtaining a prediction result comprises:
obtaining a first time difference variable of a change time and a design completion time, a second time difference variable of the change time and a manufacture start time from the time difference data, a third time difference variable of the change time and a planned trial production time, a fourth time difference variable of the design completion time and the planned trial production time, and a fifth time difference variable of the manufacture start time and the planned trial production time;
Inputting the first time difference variable, the second time difference variable, the third time difference variable, the fourth time difference variable and the fifth time difference variable into a preset machine learning algorithm to obtain the plan cost difference before and after the change of each node in the target change data;
and predicting the influence of the target change data on project planning time data and project cost data according to the time difference data and the planning cost difference to obtain a prediction result.
8. An intelligent product and manufacturing data optimizing device, characterized in that the intelligent product and manufacturing data optimizing device comprises:
the data acquisition module is used for acquiring historical BOM change data, project planning time data and project cost data;
the integrity checking module is used for carrying out integrity checking on the historical BOM change data to obtain target change data which is successfully checked;
and the prediction optimization module is used for predicting the influence of the target change data on project planning time data and project cost data, obtaining a prediction result, generating a predictive suggestion according to the prediction result, and optimizing the product manufacturing process according to the predictive suggestion.
9. A product and manufacturing data intelligent optimization apparatus, the product and manufacturing data intelligent optimization apparatus comprising: a memory, a processor, and a product and manufacturing data intelligent optimization program stored on the memory and executable on the processor, the product and manufacturing data intelligent optimization program configured to implement the steps of the product and manufacturing data intelligent optimization method of any one of claims 1-7.
10. A storage medium having stored thereon a product and manufacturing data intelligent optimization program which, when executed by a processor, performs the steps of the product and manufacturing data intelligent optimization method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311220646.6A CN117273340A (en) | 2023-09-20 | 2023-09-20 | Product and manufacturing data intelligent optimization method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311220646.6A CN117273340A (en) | 2023-09-20 | 2023-09-20 | Product and manufacturing data intelligent optimization method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117273340A true CN117273340A (en) | 2023-12-22 |
Family
ID=89200287
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311220646.6A Pending CN117273340A (en) | 2023-09-20 | 2023-09-20 | Product and manufacturing data intelligent optimization method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117273340A (en) |
-
2023
- 2023-09-20 CN CN202311220646.6A patent/CN117273340A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10685044B2 (en) | Identification and management system for log entries | |
| Yoon et al. | An approach to outlier detection of software measurement data using the k-means clustering method | |
| US8112421B2 (en) | Query selection for effectively learning ranking functions | |
| US8655918B2 (en) | System and method of transforming data for use in data analysis tools | |
| JP2008537266A (en) | Adaptive data cleaning | |
| WO2020041902A1 (en) | Analysis and correction of supply chain design through machine learning | |
| Hur et al. | A study on the man-hour prediction system for shipbuilding | |
| CN108614778B (en) | Android App program evolution change prediction method based on Gaussian process regression | |
| US9324026B2 (en) | Hierarchical latent variable model estimation device, hierarchical latent variable model estimation method, supply amount prediction device, supply amount prediction method, and recording medium | |
| CN115641162A (en) | Prediction data analysis system and method based on construction project cost | |
| CN116579804A (en) | Holiday commodity sales prediction method, holiday commodity sales prediction device and computer storage medium | |
| CN110310012B (en) | Data analysis method, device, equipment and computer readable storage medium | |
| JP2008021020A (en) | Sales plan creation support system | |
| CN101256646A (en) | Car client requirement information cluster analysis system | |
| Lugaresi et al. | Automated digital twin generation of manufacturing systems with complex material flows: graph model completion | |
| CN111046947B (en) | Training system and method of classifier and recognition method of abnormal sample | |
| CN110597796B (en) | Big data real-time modeling method and system based on full life cycle | |
| Jeyaraman et al. | Practical Machine Learning with R: Define, build, and evaluate machine learning models for real-world applications | |
| CN117273340A (en) | Product and manufacturing data intelligent optimization method, device, equipment and storage medium | |
| CN115689334A (en) | Efficiency analysis method and system of warehouse management system and computer equipment | |
| KR20230052010A (en) | Demand forecasting method using ai-based model selector algorithm | |
| CN114490571A (en) | Modeling method, server and storage medium | |
| KR102432126B1 (en) | Data preparation method and data utilization system for data use | |
| Ahsan et al. | Program File Bug Fix Effort Estimation Using Machine Learning Methods for OSS. | |
| CN112215514A (en) | Operation analysis report generation method and system |
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 |