CN117474298B - Engine connecting rod production management method and system based on upstream and downstream station feedback - Google Patents
Engine connecting rod production management method and system based on upstream and downstream station feedback Download PDFInfo
- Publication number
- CN117474298B CN117474298B CN202311816966.8A CN202311816966A CN117474298B CN 117474298 B CN117474298 B CN 117474298B CN 202311816966 A CN202311816966 A CN 202311816966A CN 117474298 B CN117474298 B CN 117474298B
- Authority
- CN
- China
- Prior art keywords
- processing
- parameter analysis
- processing table
- table data
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007726 management method Methods 0.000 title claims abstract description 124
- 238000011144 upstream manufacturing Methods 0.000 title claims abstract description 124
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 48
- 238000012545 processing Methods 0.000 claims abstract description 492
- 238000004458 analytical method Methods 0.000 claims abstract description 222
- 238000001514 detection method Methods 0.000 claims abstract description 8
- 238000010276 construction Methods 0.000 claims description 72
- 238000011143 downstream manufacturing Methods 0.000 claims description 56
- 238000012360 testing method Methods 0.000 claims description 36
- 238000000034 method Methods 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000003754 machining Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 13
- 238000007405 data analysis Methods 0.000 claims description 5
- 238000003066 decision tree Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 abstract description 8
- 238000012797 qualification Methods 0.000 abstract description 4
- 238000005457 optimization Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000013468 resource allocation Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000003801 milling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000009827 uniform distribution 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- 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
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- General Factory Administration (AREA)
Abstract
The invention provides an engine connecting rod production management method and system based on upstream and downstream station feedback, and relates to the technical field of production management, wherein if the axis parallelism of an engine connecting rod is detected to be not satisfied with the preset axis parallelism, processing table data are collected to judge the preset requirement, and if the axis parallelism of the engine connecting rod is satisfied with the input processing parameter analysis model, analysis is performed; if the input processing table management model is not satisfied, an output scheme is executed, data detection and parameter analysis are performed, processing parameter adjustment management is performed based on an analysis result, the problems that in the prior art, supervision analysis of real-time production is not strict enough, abnormal processing sources cannot be accurately positioned, production adjustment performed later and actual processing matching degree are insufficient, production management is limited are solved, processing quality qualification judgment is performed based on axis parallelism, processing table data and processing parameters are analyzed step by step, abnormal processing sources are accurately positioned, and modeling and determining analysis results are used for targeted accurate regulation and optimization management are solved.
Description
Technical Field
The invention relates to the technical field of production management, in particular to an engine connecting rod production management method and system based on upstream and downstream station feedback.
Background
The engine connecting rod is used as a main production part, the processing quality of the engine connecting rod influences the service state of the engine, the production management of the connecting rod needs to be strictly controlled, and the production adjustment management of the engine connecting rod is mainly carried out through production monitoring and periodical operation and maintenance at present, so that certain technical limitations exist.
When the production management of the engine connecting rod is carried out based on the prior art, the supervision and analysis of real-time production is not strict enough and the abnormal processing source cannot be accurately positioned, so that the matching degree of the production adjustment executed in the later step and the actual processing is insufficient, and the production management is limited.
Disclosure of Invention
The application provides an engine connecting rod production management method and system based on upstream and downstream station feedback, which are used for solving the technical problems that in the prior art, supervision and analysis on real-time production is not strict enough and abnormal processing sources cannot be accurately positioned, so that the matching degree of production adjustment and actual processing performed in the later step is insufficient, and the production management is limited.
In view of the above, the present application provides a method and a system for managing production of an engine connecting rod based on feedback of an upstream station and a downstream station.
In a first aspect, the present application provides a method for managing production of an engine connecting rod based on feedback of upstream and downstream stations, the method comprising:
after the downstream station is processed, detecting and acquiring the axis parallelism of the engine connecting rod;
when the axis parallelism does not meet the preset axis parallelism requirement, collecting first processing table data and second processing table data of the downstream station and the upstream station, wherein the upstream station is used for processing a first surface of the engine connecting rod, and the downstream station is used for processing a second surface;
judging whether the first processing table data and the second processing table data meet the preset processing table data requirements, if yes, inputting the first processing table data, the second processing table data and the axis parallelism into a processing parameter analysis model to obtain a first upstream processing parameter analysis result and a first downstream processing parameter analysis result;
if not, inputting the first processing table data and the second processing table data into a processing table management model to obtain a processing table management scheme, managing the upstream station and the downstream station, detecting after management to obtain updated first processing table data, second processing table data and axis parallelism, and inputting the updated axis parallelism into the processing parameter analysis model to obtain a second upstream processing parameter analysis result and a second downstream processing parameter analysis result;
And adjusting and managing the processing parameters of the upstream station and the downstream station by adopting the first upstream processing parameter analysis result and the first downstream processing parameter analysis result or the second upstream processing parameter analysis result and the second downstream processing parameter analysis result.
In a second aspect, the present application provides an engine connecting rod production management system based on upstream and downstream station feedback, the system comprising:
the parallelism detection module is used for detecting and acquiring the axis parallelism of the engine connecting rod after the downstream station is processed;
the data acquisition module is used for acquiring first processing table data and second processing table data of the downstream station and the upstream station when the axis parallelism does not meet the preset axis parallelism requirement, wherein the upstream station is used for processing a first face of the engine connecting rod, and the downstream station is used for processing a second face;
the data analysis module is used for judging whether the first processing table data and the second processing table data meet the preset processing table data requirements, if yes, inputting the first processing table data, the second processing table data and the axis parallelism into a processing parameter analysis model to obtain a first upstream processing parameter analysis result and a first downstream processing parameter analysis result;
The management analysis module is used for inputting the first processing table data and the second processing table data into a processing table management model if not, obtaining a processing table management scheme, managing the upstream station and the downstream station, detecting and obtaining updated first processing table data, second processing table data and axis parallelism after management, and inputting the updated axis parallelism into the processing parameter analysis model to obtain a second upstream processing parameter analysis result and a second downstream processing parameter analysis result;
and the processing management module is used for adjusting and managing the processing parameters of the upstream station and the downstream station by adopting the first upstream processing parameter analysis result and the first downstream processing parameter analysis result or the second upstream processing parameter analysis result and the second downstream processing parameter analysis result.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the engine connecting rod production management method based on the upstream and downstream station feedback, after the downstream station is processed, the axis parallelism of the engine connecting rod is detected and obtained, if the preset axis parallelism requirement is not met, first processing table data and second processing table data of the downstream station and the upstream station are collected, the upstream station is used for processing the first surface of the engine connecting rod, the downstream station is used for processing the second surface, whether the preset processing table data requirement is met is further judged, if yes, the first processing table data, the second processing table data and the axis parallelism are input into a processing parameter analysis model, and a first upstream processing parameter analysis result and a first downstream processing parameter analysis result are obtained; if not, inputting the first processing table data and the second processing table data into a processing table management model to obtain a processing table management scheme for managing an upstream processing table and a downstream processing table, detecting and obtaining updated first processing table data, second processing table data and axis parallelism after management, inputting the updated first processing table data, the updated second processing table data and the updated axis parallelism into the processing parameter analysis model to obtain a second upstream processing parameter analysis result and a second downstream processing parameter analysis result, and carrying out processing parameter adjustment management of the upstream processing table and the downstream processing table, thereby solving the technical problems that in the prior art, supervision analysis on real-time production is not strict enough and abnormal processing sources cannot be accurately positioned, resulting in insufficient production adjustment and actual processing matching degree of later execution, limiting production management, carrying out processing quality qualification judgment based on axis parallelism, analyzing gradually aiming at processing table data and processing parameters, accurately positioning abnormal processing sources, and modeling, determining analysis results, and carrying out targeted accurate regulation and optimization management.
Drawings
FIG. 1 is a schematic flow diagram of an engine connecting rod production management method based on upstream and downstream station feedback;
FIG. 2 is a schematic flow chart of a first upstream processing parameter analysis result and a first downstream processing parameter analysis result in an engine connecting rod production management method based on upstream and downstream station feedback;
FIG. 3 is a schematic diagram of a process table management scheme in an engine connecting rod production management method based on upstream and downstream station feedback;
fig. 4 is a schematic structural diagram of an engine connecting rod production management system based on feedback of upstream and downstream stations.
Reference numerals illustrate: parallelism detection module 11, data acquisition module 12, data analysis module 13, management analysis module 14, processing management module 15.
Detailed Description
The method and the system for managing the production of the engine connecting rod based on the feedback of the upstream and downstream stations are used for detecting the axis parallelism of the engine connecting rod, if the axis parallelism requirement is not met, collecting the processing table data of the downstream stations and the upstream stations to judge whether the processing table data requirement is met, and if yes, inputting the processing table data into a processing parameter analysis model for analysis; if not, a processing table management scheme is obtained in the processing table management model, data detection and parameter analysis are carried out after management, and processing parameter adjustment management of an upstream station and a downstream station is carried out, so that the technical problem that in the prior art, supervision analysis on real-time production is not strict enough and abnormal processing sources cannot be accurately positioned, and the production adjustment and actual processing matching degree carried out in the later step is insufficient, so that production management is limited is solved.
Example 1
As shown in fig. 1, the present application provides an engine connecting rod production management method based on upstream and downstream station feedback, the method comprising:
step S100: after the downstream station is processed, detecting and acquiring the axis parallelism of the engine connecting rod;
specifically, an engine connecting rod is used as a main production part, the processing quality of the engine connecting rod influences the service state of an engine, production management of the connecting rod is strictly controlled, and the method for managing production of the engine connecting rod based on the upstream and the downstream provided by the application uses the axis parallelism as a processing quality measurement index, combines corresponding processing table data to carry out processing table management and parameter analysis, obtains an analysis result and carries out adaptation and adjustment of processing parameters so as to ensure the processing quality. Specifically, in the machining process, machining of the first face and the second face of the engine connecting rod is sequentially performed based on an upstream station and a downstream station, and after machining of the downstream station is completed, namely double-face machining is completed, machining quality detection is performed on the engine connecting rod. And (3) respectively detecting the axis parallelism of the engine connecting rod aiming at a plurality of processing samples, analyzing the detection result, determining the representative axis parallelism for measuring the processing quality, and carrying out qualification judgment on the representative axis parallelism so as to carry out precision analysis on the processing parameters of the workbench.
Further, after the downstream station processing is completed, detecting and acquiring the axis parallelism of the engine connecting rod, step S100 of the present application further includes:
step S110: after the upstream station and the downstream station are matched to finish machining of the P-piece engine connecting rod, testing to obtain P test axis parallelism of the P-piece engine connecting rod, wherein P is an integer greater than 1;
step S120: when at least one test axis parallelism is not qualified, Q unqualified axis parallelism which is not qualified in the P test axis parallelism is obtained, wherein Q is an integer which is more than or equal to 1 and less than or equal to P;
step S130: clustering the same test axis parallelism in the Q unqualified axis parallelism to obtain a plurality of clustering results, and carrying out weighted calculation on the test axis parallelism of the plurality of clustering results according to the number of the unqualified axis parallelism in the plurality of clustering results to obtain the axis parallelism.
Specifically, based on the two-sided milling of the engine connecting rod at the upstream station and the downstream station, after the machining of the P engine connecting rods is completed, the axis parallelism of the obtained P engine connecting rods is detected, namely, the parallelism of the axes of the big end hole and the small end hole of the engine connecting rods is measured, and the parallelism of the P test axes can be determined through direct measurement. And determining an error allowable section in combination with a processing standard, performing qualification judgment on the P test axis parallelism, and extracting the P test axis parallelism which does not meet the error allowable section to obtain the Q unqualified axis parallelism. Further, clustering is performed on the Q disqualified axis parallelism, a plurality of clustering centers are randomly determined based on the Q disqualified axis parallelism, clustering attribution is performed based on a distance nearest neighbor principle, a clustering result is determined, iteration is determined by re-performing the clustering center determination for each clustering result, data clustering is performed again, and the clustering is repeated for a plurality of times until the maximum iteration times are met, so that a plurality of clustering results are determined.
Alternatively, the same disqualified axis parallelism may be clustered to obtain a plurality of clustering results.
And counting the number of the intra-class included in the plurality of clustering results, and carrying out weight configuration based on the number, wherein the more the number of the intra-class in the clustering results is, the higher the weight value is configured, the intra-class average value calculation is respectively carried out for each clustering result, the weighted addition is carried out on the calculation results, the axis parallelism is obtained, the metering difference caused by accidental processing conditions is avoided, the representativeness of the axis parallelism is ensured, and the axis parallelism is an index for measuring the current processing quality.
If the parallelism of the P test axes is qualified, the parallelism of the axes is qualified, and the production can be continued.
Step S200: when the axis parallelism does not meet the preset axis parallelism requirement, collecting first processing table data and second processing table data of the downstream station and the upstream station, wherein the upstream station is used for processing a first surface of the engine connecting rod, and the downstream station is used for processing a second surface;
specifically, the preset axis parallelism requirement is a standard for measuring whether the machining quality meets the standard, namely, the axis parallelism is an error allowable range, for example, the axis parallelism is offset by 3 degrees, whether the axis parallelism meets the preset axis parallelism requirement is judged, if yes, the machining quality meets the standard, and the current machining promotion is continued; if the processing quality is not up to standard, the processing abnormality tracing judgment is needed. And acquiring processing table data of the downstream station and the upstream station, wherein the processing table data comprises time sequence data of a fixed structure, height, position and the like of a processing table in a processing process, acquiring first processing table data for processing the first surface of the engine connecting rod and second processing table data for processing the second surface of the engine connecting rod, and measuring the control precision and the offset state of the processing table.
Step S300: judging whether the first processing table data and the second processing table data meet the preset processing table data requirements, if yes, inputting the first processing table data, the second processing table data and the axis parallelism into a processing parameter analysis model to obtain a first upstream processing parameter analysis result and a first downstream processing parameter analysis result;
further, as shown in fig. 2, the first processing table data, the second processing table data, and the axis parallelism are input into a processing parameter analysis model to obtain a first upstream processing parameter analysis result and a first downstream processing parameter analysis result, and step S300 of the present application further includes:
step S310: acquiring a first sample processing table data set, a second sample processing table data set, a sample axis parallelism data set, a first sample upstream processing parameter analysis result set and a first sample downstream processing parameter analysis result set based on processing data of the upstream station and the downstream station in historical time;
step S320: the first sample processing table data set, the second sample processing table data set, the sample axis parallelism data set, the first sample upstream processing parameter analysis result set and the first sample downstream processing parameter analysis result set are taken as construction data to construct the processing parameter analysis model, wherein the processing parameter analysis model comprises a plurality of processing parameter analysis units;
Step S330: inputting the first processing table data, the second processing table data and the axis parallelism into the processing parameter analysis model to obtain the first upstream processing parameter analysis result and the first downstream processing parameter analysis result.
Further, step S320 of the present application further includes:
step S321: dividing and combining the sample first processing table data set, the sample second processing table data set, the sample axis parallelism data set, the sample first upstream processing parameter analysis result set and the sample first downstream processing parameter analysis result set to obtain M-set configuration data, wherein M is an integer greater than 1;
step S322: initially distributing the M-group construction data to obtain M first coefficients, wherein each first coefficient is 1/M;
step S323: constructing a first processing parameter analysis unit for training the processing parameter analysis model by adopting the M-group construction data as construction data;
step S324: testing to obtain a first accuracy of the first processing parameter analysis unit, and combining the M first coefficients to calculate to obtain M second coefficients;
step S325: adopting the M-group construction data, constructing a second processing parameter analysis unit in the processing parameter analysis model according to the M second coefficients, wherein training computing force resources of the M-group construction data are distributed according to the sizes of the M second coefficients;
Step S326: and testing to obtain the second accuracy of the second processing parameter analysis unit, and continuing to construct and obtain the plurality of processing parameter analysis units to obtain the processing parameter analysis model.
Further, the step S324 of the present application further includes:
step S3241: the M-group construction data are adopted to test the first processing parameter analysis unit, and the first accuracy rate is obtained based on an error function;
step S3242: according to the first accuracy and the M first coefficients, M second coefficients are obtained through calculation, wherein the M second coefficients are represented by the following formula:
;
wherein,for the second coefficient of the 1 st set of construction data of the M sets of construction data,/>For the first coefficient of the 1 st group of construction data in the M groups of construction data, T is the number of constructed processing parameter analysis units,/I>The first accuracy of the first processing parameter analysis unit.
Specifically, the processing table data in the standard processing state is determined, the data tolerance is determined based on the allowable error interval for cost saving, and the definition range of the standard processing table data is adjusted to be the preset processing table data requirement. And respectively judging whether the first processing table data and the second processing table data meet the preset processing table data requirements, if so, directly inputting the first processing table data and the second processing table data into the processing parameter analysis model to perform tolerance analysis adjustment of processing parameters, and if not, performing processing table management analysis to perform adjustment of the processing table.
Specifically, the processing parameter analysis model is constructed. And acquiring processing data of the upstream station and the downstream station based on the historical time, namely a set historical processing time period bordering the current time node, to obtain a sample first processing station data set, a sample second processing station data set, a sample axis parallelism data set, a sample first upstream processing parameter analysis result set and a sample first downstream processing parameter analysis result set, wherein the data are once processing data, and can be directly identified and determined. When different disqualified axis parallelism occurs in the history time, the first upstream processing parameter analysis result set of the sample and the first downstream processing parameter analysis result set of the sample include adjustment data for adjusting the processing tolerance of the first surface and the second surface at the upstream station and the downstream station, so that the disqualified axis parallelism is eliminated by adjusting the processing tolerance, namely, the first upstream processing parameter analysis result of the sample and the first downstream processing parameter analysis result of the sample can be obtained in the history time based on analysis according to the disqualified axis parallelism by a person skilled in the art.
For example, a connecting rod with unqualified axis parallelism is detected, axis parallelism is obtained, sample first processing table data and sample second processing table data of an upstream station and a downstream station are obtained, the second surface of the connecting rod, namely the downstream processing surface, is found to be 2.5mm in height difference, size distribution is close to an upper tolerance limit, for example, 2.58mm, based on the fact that the analysis result of the sample first processing table data and the sample second processing table data obtained by analysis is that the size is adjusted to a tolerance lower limit, for example, 2.43mm, and based on the same method, sample second downstream processing parameter analysis result is obtained, and the unqualified axis parallelism of the connecting rod is avoided.
And the sample first processing table data set, the sample second processing table data set, the sample axis parallelism data set, the sample first upstream processing parameter analysis result set and the sample first downstream processing parameter analysis result set are in one-to-one correspondence, and sample data are divided and mapped and combined to obtain M-group construction data.
And respectively carrying out coefficient initialization configuration on the M groups of construction data, namely uniformly configuring the coefficients to be 1/M, and acquiring the M first coefficients. And carrying out computing power resource allocation, namely uniform distribution, of the M-group construction data based on the M first coefficients, wherein the training times of each group of construction data are the same, and carrying out neural network training on the M-group construction data to generate the first processing parameter analysis unit. And further inputting sample first processing table data, sample second processing table data and sample axis parallelism data corresponding to each piece of construction data in the M-group construction data into the first processing parameter analysis unit respectively, obtaining a unit output result, carrying out result deviation calculation on the result deviation calculation with the mapped sample first upstream processing parameter analysis result and the mapped sample first downstream processing parameter analysis result based on an error function, and determining a first accuracy for measuring the output precision of the first processing parameter unit based on a result deviation value, wherein the first accuracy is in negative correlation with an average deviation value and corresponds to the M-group construction data respectively. Optionally, the M-group construction data may be used to test the first processing parameter analysis unit, and determine whether the predicted value is the same as the sample value in the construction data, so as to obtain a ratio of the construction data and M, where the prediction is successful, and obtain the first accuracy.
Further, matching and corresponding the first accuracy and the M first coefficients, and respectively inputting formulas:performing computation of the M second coefficients, wherein +.>For the second coefficient of the 1 st set of construction data of the M sets of construction data,/>For the first coefficient of the 1 st group of construction data in the M groups of construction data, T is the number of constructed processing parameter analysis units,/I>For the first accuracy of the first processing parameter analysis unit, the parameters may be obtained by the earlier steps of the embodiments of the present application, the predicted value is based on the output value of the T-th processing parameter analysis unit, and the sample value is the first upstream addition of the corresponding sample in the M-group construction dataAnd the analysis result of the working parameter and the analysis result of the first downstream working parameter of the sample.
And further, based on the M-group construction data, performing training computing power resource allocation of corresponding construction data according to the M second coefficients, for example, allocating training times of each group of construction data, wherein the larger the second coefficient is, the more the corresponding construction data training times are, and performing neural network training on the M-group construction data in the same way to generate the second processing parameter analysis unit. Further, based on the M-group construction data, testing the second processing parameter analysis unit, determining the second accuracy rate, calculating M third coefficients, and continuing construction of the third processing parameter analysis unit, wherein the specific calculation execution step is the same as the acquisition of the M second coefficients; and repeating the construction steps to construct the processing parameter analysis units until the unit construction ending condition is met, for example, the test accuracy accords with the accuracy threshold, integrating the processing parameter analysis units and arranging the processing parameter analysis units in parallel to generate the processing parameter analysis model, and constructing the model through integrated learning to effectively improve the accuracy of the model output result.
Further, the first processing table data, the second processing table data and the axis parallelism are input into the processing parameter analysis model, analysis is performed based on the plurality of processing parameter analysis units respectively, corresponding unit output results are output, recognition and correction are performed, the output result with the highest occurrence frequency is selected as the first upstream processing parameter analysis result and the first downstream processing parameter analysis result, and data analysis is performed through integrated learning modeling so as to ensure the processing data matching degree of the results.
Alternatively, the average value of the output results of the plurality of processing parameter analysis units may be calculated as the first upstream processing parameter analysis result and the first downstream processing parameter analysis result. And carrying out machining tolerance determination based on the first upstream machining parameter analysis result and the first downstream machining parameter analysis result, and avoiding disqualification of the axis parallelism of the connecting rod.
Step S400: if not, inputting the first processing table data and the second processing table data into a processing table management model to obtain a processing table management scheme, managing the upstream station and the downstream station, detecting after management to obtain updated first processing table data, second processing table data and axis parallelism, and inputting the updated axis parallelism into the processing parameter analysis model to obtain a second upstream processing parameter analysis result and a second downstream processing parameter analysis result;
Step S500: and adjusting and managing the processing parameters of the upstream station and the downstream station by adopting the first upstream processing parameter analysis result and the first downstream processing parameter analysis result or the second upstream processing parameter analysis result and the second downstream processing parameter analysis result.
Specifically, if the first processing table data and the second processing table data do not meet the preset processing table data requirement, the processing table is illustrated to deviate greatly, the processing table management model is constructed, decision analysis is performed on the first processing table data and the second processing table data, and the processing table management scheme, namely, an adjustment execution scheme aiming at the unqualified processing table is output. Based on the processing table management scheme, adjustment, calibration and management are carried out on the upstream station and the downstream station so as to ensure that the configuration of the processing table meets the standard. And acquiring the processing table data again after the processing table management, and acquiring updated first processing table data and second processing table data. And further carrying out product processing, and detecting and obtaining the axis parallelism of the engine connecting rod after the downstream station processing is finished. And inputting the updated first processing table data, the updated second processing table data and the updated axis parallelism into the processing parameter analysis model, and outputting the second upstream processing parameter analysis result and the second downstream processing parameter analysis result.
Further, based on the first upstream processing parameter analysis result and the first downstream processing parameter analysis result, or the second upstream processing parameter analysis result and the second downstream processing parameter analysis result, corresponding processing parameter analysis results are selected according to the actual judgment state, and processing parameters of the upstream station and the downstream station are adjusted and managed so as to improve processing precision and ensure production quality.
Further, as shown in fig. 3, the first processing table data and the second processing table data are input into a processing table management model to obtain a processing table management scheme, and step S400 of the present application further includes:
step S410: acquiring a sample first processing table data set, a sample second processing table data set and a sample processing table management scheme set based on the management data of the upstream station and the downstream station in the history time;
step S420: the first sample processing table data set, the second sample processing table data set and the sample processing table management scheme set are adopted as construction data, and the processing table management model is constructed based on a decision tree, wherein the processing table management model comprises a first input channel and a second input channel;
step S430: and inputting the first processing table data and the second processing table data into the first input channel and the second input channel respectively to obtain the processing table management scheme.
Further, the first processing table data set, the second processing table data set and the sample processing table management scheme set are used as construction data, and the processing table management model is constructed based on a decision tree, so that step S420 of the present application further includes:
step S421: constructing a first decision feature based on first process table data, and constructing the first input channel;
step S422: constructing a plurality of layers of first decision nodes by adopting the sample first processing table data set, and combining the first input channels to obtain a first decision branch, wherein each layer of first decision nodes carries out classification judgment decision on the input first processing table data;
step S423: constructing a second decision feature based on second processing table data, constructing a second input channel, constructing a plurality of layers of second decision nodes by adopting the sample second processing table data set, and combining the second input channel to obtain a second decision branch;
step S424: and connecting the first decision branch with the second decision branch, acquiring a plurality of final decision results of the multi-layer first decision node and the multi-layer second decision node, and marking the plurality of final decision results by adopting a plurality of sample processing table management schemes in the sample processing table management scheme set to acquire the processing table management model.
Specifically, if the first processing table data and the second processing table data do not meet the preset processing table data requirement, the processing table is adjusted first, then processing parameter analysis is executed, and tuning management is performed by accurately positioning abnormal processing parameters. Specifically, the first sample processing table data set and the second sample processing table data set are called, processing table management schemes corresponding to the upstream station and the downstream station in the history time are collected, the sample processing table management scheme set is obtained, and the sample processing table management scheme set is an executed scheme. And the first sample processing table data set and the second sample processing table data set are in one-to-one correspondence with the sample processing table management scheme, and are mapped and associated to be used as the construction data. And training and generating the processing table management model based on the construction data, namely, performing scheme for adjusting the processing table.
Constructing the processing table management model, specifically, constructing the first decision feature based on the first processing table data, namely measuring the feature of the state of the processing table corresponding to the upstream station, such as the relative position of a fixed structure or the height of the processing table, randomly extracting data based on the sample first processing table data set, embedding the data into a constructed first decision layer, and executing two classifications on the sample first processing table data set as a decision node; randomly extracting data based on the sample first processing table data set again, embedding a constructed second decision layer, and dividing the classification result of the previous step again as a decision node; and similarly, determining decision layer construction and corresponding decision nodes for multiple times, respectively executing two classifications on the classification results of the previous step until a preset condition is met, for example, the maximum construction layer number is reached, performing hierarchical connection of the decision nodes, and obtaining the multi-layer first decision nodes. The first input channel is constructed and used for transmitting the data of the first processing table, the multi-layer first decision nodes are embedded in the first input channel and used as the first decision branches, and the first decision branches are used for carrying out hierarchical decision attribution on the input data of the first processing table.
And similarly, determining the characteristic for measuring the state of the processing table corresponding to the downstream station based on the second processing table data as the second decision feature. And further constructing the second input channel for performing transmission of second processing station data. And constructing the multi-layer second decision nodes based on the sample second processing table data set, wherein the construction modes of the multi-layer second decision nodes are the same, and specific construction data are different. Embedding the multi-layer second decision node into the second input channel, and acquiring the second decision branch, wherein the second decision branch is used for carrying out hierarchical decision attribution on the input second processing table data.
And further, the first decision branch and the second decision branch are connected in series, for example, a top layer node of a multi-layer first decision node and a bottom layer node of a multi-layer second decision node are connected, the connected first decision branch and second decision branch can carry out multi-layer division decision on the input first processing table data, then carry out multi-layer division decision on the input second processing table data again, and obtain a comprehensive decision result.
And obtaining a plurality of final decision results after the multi-layer first decision nodes and the multi-layer second decision nodes carry out multi-layer division decisions. And based on the sample processing management scheme set, performing matching marks of the multiple final decision results to generate the processing table management model, so that the adjustment scheme of the processing table can be rapidly and accurately determined.
Further, the first processing table data is input into the first input channel in the processing table management model, the second processing table data is input into the second input channel in the processing table management model, hierarchical decision attribution of input data is respectively carried out on the basis of the multi-layer first decision nodes and the multi-layer second decision nodes embedded in the channels, final decision results corresponding to attribution results are determined, mark recognition is carried out to serve as a processing table management scheme, and adjustment of a processing table is carried out on the basis of the processing table management scheme so as to avoid that the processing quality is not affected by the processing table reaching standards.
Example 2
Based on the same inventive concept as the engine connecting rod production management method based on the feedback of the upstream and downstream stations in the foregoing embodiments, as shown in fig. 4, the present application provides an engine connecting rod production management system based on the feedback of the upstream and downstream stations, the system comprising:
the parallelism detection module 11 is used for detecting and acquiring the axis parallelism of the engine connecting rod after the downstream station is processed;
the data acquisition module 12 is configured to acquire first processing table data and second processing table data of the downstream station and the upstream station when the axis parallelism does not meet a preset axis parallelism requirement, where the upstream station processes a first face of the engine connecting rod, and the downstream station is configured to process a second face;
The data analysis module 13 is configured to determine whether the first processing table data and the second processing table data meet a preset processing table data requirement, if yes, input the first processing table data, the second processing table data and the axis parallelism into a processing parameter analysis model, and obtain a first upstream processing parameter analysis result and a first downstream processing parameter analysis result;
the management analysis module 14 is configured to, if not, input the first processing table data and the second processing table data into a processing table management model to obtain a processing table management scheme, manage the upstream station and the downstream station, detect and obtain updated first processing table data, second processing table data and axis parallelism after management, and input the updated axis parallelism into the processing parameter analysis model to obtain a second upstream processing parameter analysis result and a second downstream processing parameter analysis result;
the processing management module 15 is configured to adjust and manage the processing parameters of the upstream station and the downstream station by using the first upstream processing parameter analysis result and the first downstream processing parameter analysis result, or the second upstream processing parameter analysis result and the second downstream processing parameter analysis result.
Further, the system further comprises:
the axis testing module is used for testing and obtaining the parallelism of P testing axes of the P engine connecting rods after the P engine connecting rods are matched with the upstream station and the downstream station to finish processing, wherein P is an integer greater than 1;
the parallelism acquisition module is used for acquiring Q unqualified axis parallelism which are unqualified in the P test axis parallelism when at least one test axis parallelism is unqualified, wherein Q is an integer which is more than or equal to 1 and less than or equal to P;
and the clustering calculation module is used for clustering the same test axis parallelism in the Q unqualified axis parallelism to obtain a plurality of clustering results, and carrying out weighted calculation on the test axis parallelism of the plurality of clustering results according to the number of the unqualified axis parallelism in the plurality of clustering results to obtain the axis parallelism.
Further, the system further comprises:
the sample data acquisition module is used for acquiring a sample first processing table data set, a sample second processing table data set, a sample axis parallelism data set, a sample first upstream processing parameter analysis result set and a sample first downstream processing parameter analysis result set based on processing data of the upstream station and the downstream station in historical time;
The model construction module is used for constructing the processing parameter analysis model by adopting the sample first processing table data set, the sample second processing table data set, the sample axis parallelism data set, the sample first upstream processing parameter analysis result set and the sample first downstream processing parameter analysis result set as construction data, wherein the processing parameter analysis model comprises a plurality of processing parameter analysis units;
and the model analysis module is used for inputting the first processing table data, the second processing table data and the axis parallelism into the processing parameter analysis model to obtain the first upstream processing parameter analysis result and the first downstream processing parameter analysis result.
Further, the system further comprises:
the sample dividing and combining module is used for dividing and combining the sample first processing table data set, the sample second processing table data set, the sample axis parallelism data set, the sample first upstream processing parameter analysis result set and the sample first downstream processing parameter analysis result set to obtain M groups of construction data, wherein M is an integer greater than 1;
The first coefficient acquisition module is used for obtaining M first coefficients through initial distribution of the M groups of construction data, and each first coefficient is 1/M;
the first processing parameter analysis unit construction module is used for constructing and training a first processing parameter analysis unit in the processing parameter analysis model by adopting the M group construction data as construction data;
the second coefficient calculation module is used for testing and obtaining the first accuracy of the first processing parameter analysis unit, and combining the M first coefficients to calculate and obtain M second coefficients;
the second processing parameter analysis unit construction module is used for constructing a second processing parameter analysis unit in the processing parameter analysis model according to the M second coefficients by adopting the M-group construction data, wherein training calculation force resources of the M-group construction data are distributed according to the sizes of the M second coefficients;
and the processing parameter analysis model acquisition module is used for testing and obtaining the second accuracy of the second processing parameter analysis unit, and continuously constructing and obtaining the plurality of processing parameter analysis units to obtain the processing parameter analysis model.
Further, the system further comprises:
the first accuracy acquisition module is used for testing the first processing parameter analysis unit by adopting the M-group construction data and acquiring the first accuracy based on an error function;
the coefficient calculation module is used for calculating and obtaining M second coefficients according to the first accuracy and the M first coefficients, and the formula is as follows:
;
wherein,for the second coefficient of the 1 st set of construction data of the M sets of construction data,/>For the first coefficient of the 1 st group of construction data in the M groups of construction data, T is the number of constructed processing parameter analysis units,/I>The first accuracy of the first processing parameter analysis unit.
Further, the system further comprises:
the sample management data acquisition module is used for acquiring a sample first processing table data set, a sample second processing table data set and a sample processing table management scheme set based on management data of the upstream station and the downstream station in historical time;
the processing table management model building module is used for building the processing table management model based on a decision tree by adopting the sample first processing table data set, the sample second processing table data set and the sample processing table management scheme set as building data, and comprises a first input channel and a second input channel;
The scheme acquisition module is used for inputting the first processing table data and the second processing table data into the first input channel and the second input channel respectively to obtain the processing table management scheme.
Further, the system further comprises:
the first input channel construction module is used for constructing a first decision feature based on first processing table data and constructing the first input channel;
the first decision branch acquisition module is used for constructing a plurality of layers of first decision nodes by adopting the sample first processing table data set and acquiring a first decision branch by combining the first input channel, wherein each layer of first decision nodes carries out classification judgment decision on the input first processing table data;
the second decision branch acquisition module is used for constructing a second decision feature based on second processing table data, constructing the second input channel, constructing a plurality of layers of second decision nodes by adopting the sample second processing table data set, and acquiring a second decision branch by combining the second input channel;
The model acquisition module is used for connecting the first decision branch and the second decision branch, acquiring a plurality of final decision results of the multi-layer first decision node and the multi-layer second decision node, and marking the plurality of final decision results by adopting a plurality of sample processing table management schemes in the sample processing table management scheme set to obtain the processing table management model.
Through the foregoing detailed description of an engine connecting rod production management method based on the feedback of the upstream and downstream stations, those skilled in the art can clearly know an engine connecting rod production management method and system based on the feedback of the upstream and downstream stations in this embodiment, and for the device disclosed in the embodiment, since the device corresponds to the method disclosed in the embodiment, the description is relatively simple, and relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. An engine connecting rod production management method based on upstream and downstream station feedback, which is characterized by comprising the following steps:
after the downstream station is processed, detecting and acquiring the axis parallelism of the engine connecting rod;
when the axis parallelism does not meet the preset axis parallelism requirement, collecting first processing table data and second processing table data of the downstream station and the upstream station, wherein the upstream station is used for processing a first surface of the engine connecting rod, and the downstream station is used for processing a second surface;
judging whether the first processing table data and the second processing table data meet the preset processing table data requirements, if yes, inputting the first processing table data, the second processing table data and the axis parallelism into a processing parameter analysis model to obtain a first upstream processing parameter analysis result and a first downstream processing parameter analysis result;
if not, inputting the first processing table data and the second processing table data into a processing table management model to obtain a processing table management scheme, managing the upstream station and the downstream station, detecting after management to obtain updated first processing table data, second processing table data and axis parallelism, and inputting the updated axis parallelism into the processing parameter analysis model to obtain a second upstream processing parameter analysis result and a second downstream processing parameter analysis result;
And adjusting and managing the processing parameters of the upstream station and the downstream station by adopting the first upstream processing parameter analysis result and the first downstream processing parameter analysis result or the second upstream processing parameter analysis result and the second downstream processing parameter analysis result.
2. The method of claim 1, wherein detecting the parallelism of the axis of the engine connecting rod after the downstream processing is completed comprises:
after the upstream station and the downstream station are matched to finish machining of the P-piece engine connecting rod, testing to obtain P test axis parallelism of the P-piece engine connecting rod, wherein P is an integer greater than 1;
when at least one test axis parallelism is not qualified, Q unqualified axis parallelism which is not qualified in the P test axis parallelism is obtained, wherein Q is an integer which is more than or equal to 1 and less than or equal to P;
clustering the same test axis parallelism in the Q unqualified axis parallelism to obtain a plurality of clustering results, and carrying out weighted calculation on the test axis parallelism of the plurality of clustering results according to the number of the unqualified axis parallelism in the plurality of clustering results to obtain the axis parallelism.
3. The method of claim 1, wherein inputting the first process table data, the second process table data, and the axis parallelism into a process parameter analysis model to obtain a first upstream process parameter analysis result and a first downstream process parameter analysis result comprises:
acquiring a first sample processing table data set, a second sample processing table data set, a sample axis parallelism data set, a first sample upstream processing parameter analysis result set and a first sample downstream processing parameter analysis result set based on processing data of the upstream station and the downstream station in historical time;
the first sample processing table data set, the second sample processing table data set, the sample axis parallelism data set, the first sample upstream processing parameter analysis result set and the first sample downstream processing parameter analysis result set are taken as construction data to construct the processing parameter analysis model, wherein the processing parameter analysis model comprises a plurality of processing parameter analysis units;
inputting the first processing table data, the second processing table data and the axis parallelism into the processing parameter analysis model to obtain the first upstream processing parameter analysis result and the first downstream processing parameter analysis result.
4. A method according to claim 3, characterized in that the method comprises:
dividing and combining the sample first processing table data set, the sample second processing table data set, the sample axis parallelism data set, the sample first upstream processing parameter analysis result set and the sample first downstream processing parameter analysis result set to obtain M-set configuration data, wherein M is an integer greater than 1;
initially distributing the M-group construction data to obtain M first coefficients, wherein each first coefficient is 1/M;
constructing a first processing parameter analysis unit for training the processing parameter analysis model by adopting the M-group construction data as construction data;
testing to obtain a first accuracy of the first processing parameter analysis unit, and combining the M first coefficients to calculate to obtain M second coefficients;
adopting the M-group construction data, constructing a second processing parameter analysis unit in the processing parameter analysis model according to the M second coefficients, wherein training computing force resources of the M-group construction data are distributed according to the sizes of the M second coefficients;
and testing to obtain the second accuracy of the second processing parameter analysis unit, and continuing to construct and obtain the plurality of processing parameter analysis units to obtain the processing parameter analysis model.
5. The method of claim 4, wherein testing to obtain a first accuracy of the first process parameter analysis unit and calculating to obtain M second coefficients in combination with the M first coefficients comprises:
the M-group construction data are adopted to test the first processing parameter analysis unit, and the first accuracy rate is obtained based on an error function;
according to the first accuracy and the M first coefficients, M second coefficients are obtained through calculation, wherein the M second coefficients are represented by the following formula:
;
wherein,for the second coefficient of the 1 st set of construction data of the M sets of construction data,/>For the first coefficient of the 1 st group of construction data in the M groups of construction data, T is the number of constructed processing parameter analysis units,/I>The first accuracy of the first processing parameter analysis unit.
6. The method of claim 1, wherein inputting the first and second process station data into a process station management model to obtain a process station management recipe comprises:
acquiring a sample first processing table data set, a sample second processing table data set and a sample processing table management scheme set based on the management data of the upstream station and the downstream station in the history time;
The first sample processing table data set, the second sample processing table data set and the sample processing table management scheme set are adopted as construction data, and the processing table management model is constructed based on a decision tree, wherein the processing table management model comprises a first input channel and a second input channel;
and inputting the first processing table data and the second processing table data into the first input channel and the second input channel respectively to obtain the processing table management scheme.
7. The method of claim 6, wherein using the sample first process station dataset, sample second process station dataset, and sample process station management recipe set as build data, building the process station management model based on a decision tree, comprises:
constructing a first decision feature based on first process table data, and constructing the first input channel;
constructing a plurality of layers of first decision nodes by adopting the sample first processing table data set, and combining the first input channels to obtain a first decision branch, wherein each layer of first decision nodes carries out classification judgment decision on the input first processing table data;
constructing a second decision feature based on second processing table data, constructing a second input channel, constructing a plurality of layers of second decision nodes by adopting the sample second processing table data set, and combining the second input channel to obtain a second decision branch;
And connecting the first decision branch with the second decision branch, acquiring a plurality of final decision results of the multi-layer first decision node and the multi-layer second decision node, and marking the plurality of final decision results by adopting a plurality of sample processing table management schemes in the sample processing table management scheme set to acquire the processing table management model.
8. An engine connecting rod production management system based on upstream and downstream station feedback, the system comprising:
the parallelism detection module is used for detecting and acquiring the axis parallelism of the engine connecting rod after the downstream station is processed;
the data acquisition module is used for acquiring first processing table data and second processing table data of the downstream station and the upstream station when the axis parallelism does not meet the preset axis parallelism requirement, wherein the upstream station is used for processing a first face of the engine connecting rod, and the downstream station is used for processing a second face;
the data analysis module is used for judging whether the first processing table data and the second processing table data meet the preset processing table data requirements, if yes, inputting the first processing table data, the second processing table data and the axis parallelism into a processing parameter analysis model to obtain a first upstream processing parameter analysis result and a first downstream processing parameter analysis result;
The management analysis module is used for inputting the first processing table data and the second processing table data into a processing table management model if not, obtaining a processing table management scheme, managing the upstream station and the downstream station, detecting and obtaining updated first processing table data, second processing table data and axis parallelism after management, and inputting the updated axis parallelism into the processing parameter analysis model to obtain a second upstream processing parameter analysis result and a second downstream processing parameter analysis result;
and the processing management module is used for adjusting and managing the processing parameters of the upstream station and the downstream station by adopting the first upstream processing parameter analysis result and the first downstream processing parameter analysis result or the second upstream processing parameter analysis result and the second downstream processing parameter analysis result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311816966.8A CN117474298B (en) | 2023-12-27 | 2023-12-27 | Engine connecting rod production management method and system based on upstream and downstream station feedback |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311816966.8A CN117474298B (en) | 2023-12-27 | 2023-12-27 | Engine connecting rod production management method and system based on upstream and downstream station feedback |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117474298A CN117474298A (en) | 2024-01-30 |
| CN117474298B true CN117474298B (en) | 2024-04-02 |
Family
ID=89631521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311816966.8A Active CN117474298B (en) | 2023-12-27 | 2023-12-27 | Engine connecting rod production management method and system based on upstream and downstream station feedback |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117474298B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109839053A (en) * | 2017-11-29 | 2019-06-04 | 江苏科技大学 | A kind of measuring device and measuring method of the large and small head bore depth of parallelism of connecting rod |
| CN110238649A (en) * | 2019-06-19 | 2019-09-17 | 北京理工大学 | A kind of reconfigurable man-machine coordination assembly system for aero-engine |
| CN114433745A (en) * | 2022-03-04 | 2022-05-06 | 杭州沃瑞奥汽车零部件有限公司 | Manufacturing process of signal panel part with cleanliness requirement |
| CN116341038A (en) * | 2023-03-21 | 2023-06-27 | 内江金鸿曲轴有限公司 | Method, system, equipment and storage medium for machining crankshaft center hole |
-
2023
- 2023-12-27 CN CN202311816966.8A patent/CN117474298B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109839053A (en) * | 2017-11-29 | 2019-06-04 | 江苏科技大学 | A kind of measuring device and measuring method of the large and small head bore depth of parallelism of connecting rod |
| CN110238649A (en) * | 2019-06-19 | 2019-09-17 | 北京理工大学 | A kind of reconfigurable man-machine coordination assembly system for aero-engine |
| CN114433745A (en) * | 2022-03-04 | 2022-05-06 | 杭州沃瑞奥汽车零部件有限公司 | Manufacturing process of signal panel part with cleanliness requirement |
| CN116341038A (en) * | 2023-03-21 | 2023-06-27 | 内江金鸿曲轴有限公司 | Method, system, equipment and storage medium for machining crankshaft center hole |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117474298A (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115833400B (en) | Monitoring and early warning method and system for power equipment of transformer substation | |
| CN109902931B (en) | Operation risk modeling method of multi-state manufacturing system based on operation data fusion | |
| WO2014157748A1 (en) | Apparatus and method for predicting rate of flow and concentration of constituents flowing into sewage treatment plant using nearest neighbor technique | |
| CN105163326A (en) | Cell clustering method and system based on wireless network traffic features | |
| CN116224930B (en) | Processing control method and system for numerically controlled grinder product | |
| CN103177289B (en) | Modeling method for noise-uncertainty complicated nonlinear dynamic system | |
| CN117008557B (en) | Production control method and system for blending type interpenetrating network thermoplastic elastomer | |
| CN108198268B (en) | Production equipment data calibration method | |
| CN110298369A (en) | A kind of discrimination method and system of electric system bad data | |
| CN114486764A (en) | Agricultural non-point source pollution monitoring system based on full-spectrum water quality analyzer | |
| CN116307405B (en) | Diode performance prediction method and system based on production data | |
| CN108563201B (en) | DMAIC-driven small-batch part machining process quality improvement method | |
| CN110110339A (en) | A kind of hydrologic forecast error calibration method and system a few days ago | |
| CN117474298B (en) | Engine connecting rod production management method and system based on upstream and downstream station feedback | |
| CN117129556B (en) | Indoor TVOC concentration real-time monitoring system based on wireless sensor network | |
| Wong et al. | A mobile production monitoring system based on internet of thing (IoT) and random forest classification | |
| CN114339477A (en) | Data acquisition management method and system based on multi-table integration | |
| CN111080115B (en) | Water consumption distribution method and device based on water supply hydraulic model | |
| CN106341837A (en) | Inferior quality telephone traffic proportion value prediction method and device | |
| CN117829821B (en) | Cloud platform-based composite material equipment maintenance and management method | |
| CN109918220A (en) | A kind of anomaly data detection determination method for parameter and determining device | |
| CN109376337B (en) | Distributed soft measurement method based on Girvan-Newman algorithm | |
| CN117469603B (en) | Multi-water-plant water supply system pressure optimal control method based on big data learning | |
| CN117048113B (en) | Dynamic precision detection method and system for stamping aluminum foil cutlery box | |
| CN117408572B (en) | Preparation optimization method and system of electrochromic elastic film |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |