CN118278825B - Product error data analysis system and method based on planned production - Google Patents
Product error data analysis system and method based on planned production Download PDFInfo
- Publication number
- CN118278825B CN118278825B CN202410702523.4A CN202410702523A CN118278825B CN 118278825 B CN118278825 B CN 118278825B CN 202410702523 A CN202410702523 A CN 202410702523A CN 118278825 B CN118278825 B CN 118278825B
- Authority
- CN
- China
- Prior art keywords
- production
- data
- product
- link
- change trend
- 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
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 409
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000007405 data analysis Methods 0.000 title claims abstract description 24
- 230000000694 effects Effects 0.000 claims abstract description 30
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- 238000000556 factor analysis Methods 0.000 claims abstract description 19
- 238000013441 quality evaluation Methods 0.000 claims abstract description 16
- 238000011156 evaluation Methods 0.000 claims abstract description 12
- 230000008859 change Effects 0.000 claims description 88
- 238000012797 qualification Methods 0.000 claims description 62
- 238000004088 simulation Methods 0.000 claims description 36
- 238000004364 calculation method Methods 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 15
- 239000000284 extract Substances 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000003908 quality control method Methods 0.000 claims description 5
- 238000013461 design Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract 1
- 230000003993 interaction Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000002699 waste material Substances 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Factory Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a product error data analysis system and method based on planned production, and belongs to the technical field of data analysis. The system of the invention comprises: the device comprises a data acquisition module, a quality evaluation module, a trend analysis module, an influence factor analysis and adjustment module and an effect evaluation and feedback module; the output end of the data acquisition module is connected with the input end of the quality evaluation module; the output end of the quality evaluation module is connected with the input end of the trend analysis module; the output end of the trend analysis module is connected with the input end of the influence factor analysis and adjustment module; the output end of the influence factor analysis and adjustment module is connected with the input end of the effect evaluation and feedback module; according to the invention, through links such as data acquisition, quality evaluation, trend analysis, influence factor analysis and adjustment, effect evaluation and feedback, the dynamic monitoring, analysis and adjustment of error data in the production process of the product are realized, so that the production quality of the product is improved.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a product error data analysis system and method based on planned production.
Background
With the increasing development of industrial production, error control in the product manufacturing process is becoming more and more important. The presence of errors not only affects the performance and quality of the product, but may also lead to increased production costs and waste of resources. Therefore, how to effectively analyze and manage the error data in the production process becomes the key for improving the quality and the production efficiency of the product,
Currently, many enterprises employ various error data analysis methods to monitor the error conditions during the production process. However, these methods typically focus only on the statistics and analysis of the error data, and ignore the root cause of the error generation and how to take effective measures to reduce the error. In addition, the existing error data analysis method often lacks unified standards and standards, so that the error data analysis result has great subjectivity and uncertainty.
Disclosure of Invention
The invention aims to provide a product error data analysis system and method based on planned production, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme:
a product error data analysis method based on programming production comprises the following steps:
S100, acquiring planning information of the whole production process of the product and production data of different batches of products, dividing the production data according to production links corresponding to the planning information, and forming a plurality of production link historical data sets;
Step S200, obtaining the production qualification rate of products in different batches, and evaluating the quality score of the production link for each element of the historical data set of all the production links; dividing the production data of the products corresponding to each batch into error data and normal data according to the quality scores of the production links, and analyzing the error data and the normal data of the same production links of different batches to obtain an error data change trend coefficient and a normal data change trend coefficient;
S300, analyzing the error data change trend coefficient and the normal data change trend coefficient, finding out influence factors related to the normal data change trend coefficient, and dynamically adjusting data values of the influence factors of the production links with error data with reference to the corresponding production links of the normal data;
S400, obtaining the adjusted product production qualification rate, comparing the adjusted product production qualification rate with the product production qualification rate before adjustment, judging the dynamic adjustment effect of the production links according to the comparison result, and outputting the dynamic adjustment effect of all the production links to related personnel for further processing by the related personnel.
Further, step S100 includes the following:
S101, planning information of the whole production process of the product refers to overall planning and design of the production process of the product, and the planning information comprises specific working contents, production standards and qualified product production data of a production link; the product production data refer to data collected in the production process of the product, including production process data, equipment operation data and quality control data; the production process data refer to process parameters used in various links in the production process, such as temperature, pressure, speed, time, proportion and the like; the equipment operation data refer to data related to the operation state of production equipment, including starting and stopping time of the equipment, working efficiency of the equipment and the like; the quality control data refers to quality inspection data such as product size, weight, composition, surface quality, appearance, etc. performed during or after the production process;
S102, acquiring planning information of the whole production process of the product and production data of different batches of products, and acquiring production links of the product according to the planning information of the whole production process of the product; based on the production links of the products, dividing the production data of different batches of products according to the different production links so as to form a plurality of production link history data sets Ai, wherein i represents the production link numbers, ai= { a1i, a2i, and ani }, wherein a1i represents the production data of the ith production link of the 1 st batch, a2i represents the production data of the ith production link of the 2 nd batch, and so on, ani represents the production data of the ith production link of the n-th batch, and n represents the batch times.
Further, step S200 includes the following:
s201, obtaining product production qualification rates of different batches, and evaluating quality scores of production links for elements of each production link history data set by combining the production link history data set Ai and qualified product production data in planning information of the whole production process, wherein a specific calculation formula is as follows:
，
Wherein S ij represents the quality score of the ith production link of the jth batch, S ij represents the product production data of the ith production link of the jth batch, mu i represents the qualified product production data of the ith production link, sigma i represents the standard deviation of the product production data of the ith production link, and h j represents the product production qualification rate of the jth batch;
S202, obtaining quality scores of production links corresponding to elements of each production link historical data set, and respectively calculating quality score average values S0 of the production links for each production link historical data set; taking the element which is larger than or equal to the corresponding quality score average value S0 in each production link historical data set as normal data, and taking the element which is smaller than the corresponding quality score average value S0 in each production link historical data set as error data;
S203, respectively acquiring error data and normal data for each production link historical data set, so as to respectively calculate an error data change trend coefficient TC1 and a normal data change trend coefficient TC2, wherein the specific calculation formulas of the error data change trend coefficient and the normal data change trend coefficient are as follows:
，
Wherein TCb represents an error data change trend coefficient or a normal data change trend coefficient, b is 1 or 2, x k represents a value of the error data or the normal data at a kth time point, and m represents a time sequence length of the error data or the normal data.
The quality condition of each production link can be objectively evaluated by calculating the quality score of each production link and combining the historical data with the product production data; the calculation of the quality score combines the qualified product production data, the actual product production data and the standard deviation of the data, so that the stability and the accuracy in the product production process can be comprehensively considered; the quality level of each production link can be quantitatively reflected through the quality score, and guidance and reference are provided for optimizing the production process; elements in the historical data set are divided into error data and normal data, so that abnormal conditions in the production process can be recognized and distinguished; by calculating the change trend coefficients of the error data and the normal data, the change trend and regularity of the data can be analyzed.
Further, step S300 includes the following:
S301, respectively obtaining corresponding error data change trend coefficients TC1 and normal data change trend coefficients TC2 aiming at elements in each production link historical data set, and calculating deviation values R of the error data change trend coefficients TC1 and the normal data change trend coefficients TC2 of the same production link historical data set, wherein a specific calculation formula is as follows:
，
Wherein, TC2w represents the w-th normal data change trend coefficient in the same production link history data set, z represents the number of the normal data change trend coefficients in the same production link history data set, and TC20 represents the average value of the normal data change trend coefficients in the same production link history data set;
S302, acquiring a deviation value R of an error data change trend coefficient TC1 and a normal data change trend coefficient TC2 of the same production link historical data set aiming at each production link historical data set, and selecting error data with the largest deviation value R as target data; comparing target data with normal data in a historical data set of a production link one by one, so as to extract differential features between the target data and the normal data, thereby obtaining a differential feature set Bi, wherein Bi= { b1, b2, bv } i, bi represents the differential feature set of the ith production link, b1 represents the 1 st differential feature, b2 represents the 2 nd differential feature, and the like, bv represents the v differential feature, and v represents the number of differential features;
For each element in the differential feature set Bi, an influence factor corresponding to the differential feature is found, the data value of the influence factor corresponding to the target data is adjusted to the data value of the influence factor corresponding to the normal data according to the influence factor corresponding to the differential feature, and the adjusted data value of the influence factor corresponding to the target data is used as a simulation condition.
For finding out corresponding influencing factors according to the difference characteristics, the combination of some data analysis and domain knowledge is needed; firstly, carrying out detailed data analysis on the differential features, including statistical analysis, visual analysis and the like, so as to know the distribution, change rule and other conditions of the differential features; factors which may affect the differential features during the production process are known by the expert knowledge in the relevant field, and these factors may relate to various aspects of equipment, materials, processes, environment, etc., and may also help to identify the influencing factors related to the differential features by the expert or team.
Further, step S400 includes the following:
S401, regarding each production link historical data set, taking simulation conditions as initial conditions, acquiring target data, thus carrying out data simulation of corresponding production links of different batches, acquiring product simulation production data of different batches and corresponding product production qualification rate, and comparing the adjusted product production qualification rate with the product production qualification rate before adjustment;
s402, if the adjusted product production qualification rate is greater than the product production qualification rate before adjustment, storing an adjustment process; if the adjusted product production qualification rate is smaller than or equal to the product production qualification rate before adjustment, outputting prompt information to related personnel, further analyzing by the related personnel to enable the product production qualification rate after adjustment to be larger than the product production qualification rate before adjustment, and recording the analysis process of the related personnel.
For the data simulation of corresponding production links of different batches, firstly taking the data value of the influence factors corresponding to the adjusted target data as simulation conditions, including various parameters, equipment states, environmental factors and the like of the production links, wherein the conditions should cover various aspects which possibly influence the quality of products in the production process; selecting the most suitable simulation method according to actual conditions and requirements, thereby establishing a simulation model of a production link; the model can accurately reflect the interaction among all factors in the production process and the influence of the interaction on the product percent of pass; inputting the simulation conditions as initial conditions into a simulation model, and operating the simulation model to obtain simulation data; according to the set initial conditions and the simulation method, the production data of different batches of products and the corresponding product qualification rate are obtained.
A product error data analysis system based on planned production, the system comprising: the device comprises a data acquisition module, a quality evaluation module, a trend analysis module, an influence factor analysis and adjustment module and an effect evaluation and feedback module;
The data acquisition module is responsible for acquiring planning information of the whole production process of the product and production data of different batches of products, dividing the production data of the product according to production links corresponding to the planning information, and forming a plurality of production link historical data sets;
The quality evaluation module is used for carrying out quality evaluation on elements of each production link historical data set by combining the production link historical data set and qualified product production data in the planning information, evaluating quality scores of production links and dividing error data and normal data;
The trend analysis module analyzes the change trend coefficients of the error data and the normal data, calculates the deviation value of the change trend coefficient of the error data and the change trend coefficient of the normal data, and extracts the difference characteristic;
The influence factor analysis and adjustment module is used for identifying influence factors corresponding to the difference characteristics by analyzing the difference characteristics between the target data and the normal data; according to the influence factors corresponding to the difference characteristics, the data values of the influence factors corresponding to the target data are adjusted to the data values of the influence factors corresponding to the normal data;
The effect evaluation and feedback module compares the production qualification rate of the adjusted product with the production qualification rate of the product before adjustment, judges the dynamic adjustment effect of the production links according to the comparison result, outputs the dynamic adjustment effect of all the production links to related personnel, and is further processed by the related personnel.
Further, the quality evaluation module comprises a production link dividing unit and a production link quality scoring unit;
The production link dividing unit divides the production data of the product according to the planning information and the production links to form a plurality of production link historical data sets; and the production link quality scoring unit is used for evaluating the quality score of the production link for each element of all the production link historical data sets by combining the production qualification rate of the products in different batches.
Further, the trend analysis module comprises a trend coefficient calculation unit, a deviation value calculation unit and a difference characteristic extraction unit;
The trend coefficient calculation unit analyzes error data and normal data of the same production links of different batches to obtain an error data change trend coefficient and a normal data change trend coefficient; the deviation value calculating unit calculates a deviation value of the error data change trend coefficient and the normal data change trend coefficient; the difference feature extraction unit extracts a difference feature between the target data and the normal data based on the calculation result of the deviation value calculation unit.
Further, the influence factor analysis and adjustment module comprises an influence factor analysis unit and an influence factor adjustment unit;
The influence factor analysis unit analyzes corresponding influence factors based on the difference characteristics between the target data and the normal data; and the influence factor adjusting unit adjusts the data value of the influence factor corresponding to the target data according to the influence factor corresponding to the difference characteristic.
Further, the effect evaluation and feedback module comprises a simulation and comparison unit and a result feedback unit;
The simulation and comparison unit compares the adjusted product production qualification rate with the product production qualification rate before adjustment, and evaluates the dynamic adjustment effect of the production link; and the result feedback unit outputs the dynamic adjustment effect of all production links to related personnel, and prompts the related personnel to further process according to the comparison result.
Compared with the prior art, the invention has the following beneficial effects:
According to the method, the historical data set of the production link is analyzed, so that the error conditions of production of different batches of products are comprehensively considered, and the error generation condition can be more comprehensively known; according to the invention, the influence factors related to the normal data change trend coefficient are found by analyzing the error data change trend coefficient and the normal data change trend coefficient, and the production links with error data are dynamically adjusted, so that the production links can be flexibly adjusted according to actual conditions, and the product percent of pass is improved; by dynamically adjusting the error data and finding out the corresponding influence factors according to the difference characteristics to adjust, the invention can effectively reduce the root cause of the error, thereby improving the quality stability of the product; by dynamically adjusting the production links, the invention can effectively improve the production efficiency, reduce unnecessary loss caused by errors, and further improve the production efficiency and economic benefit of enterprises.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a product error data analysis system based on planned production according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides the following technical solutions:
a product error data analysis system based on planned production, the system comprising: the device comprises a data acquisition module, a quality evaluation module, a trend analysis module, an influence factor analysis and adjustment module and an effect evaluation and feedback module;
The data acquisition module is responsible for acquiring planning information of the whole production process of the product and production data of different batches of products, dividing the production data of the product according to production links corresponding to the planning information, and forming a plurality of production link historical data sets;
The quality evaluation module is used for carrying out quality evaluation on elements of each production link historical data set by combining the production link historical data set and qualified product production data in the planning information, evaluating quality scores of production links and dividing error data and normal data;
The trend analysis module analyzes the change trend coefficients of the error data and the normal data, calculates the deviation value of the change trend coefficient of the error data and the change trend coefficient of the normal data, and extracts the difference characteristic;
The influence factor analysis and adjustment module is used for identifying influence factors corresponding to the difference characteristics by analyzing the difference characteristics between the target data and the normal data; according to the influence factors corresponding to the difference characteristics, the data values of the influence factors corresponding to the target data are adjusted to the data values of the influence factors corresponding to the normal data;
The effect evaluation and feedback module compares the production qualification rate of the adjusted product with the production qualification rate of the product before adjustment, judges the dynamic adjustment effect of the production links according to the comparison result, outputs the dynamic adjustment effect of all the production links to related personnel, and is further processed by the related personnel.
The quality evaluation module comprises a production link dividing unit and a production link quality scoring unit;
The production link dividing unit divides the production data of the product according to the planning information and the production links to form a plurality of production link historical data sets; and the production link quality scoring unit is used for evaluating the quality score of the production link for each element of all the production link historical data sets by combining the production qualification rate of the products in different batches.
The trend analysis module comprises a trend coefficient calculation unit, a deviation value calculation unit and a difference characteristic extraction unit;
The trend coefficient calculation unit analyzes error data and normal data of the same production links of different batches to obtain an error data change trend coefficient and a normal data change trend coefficient; the deviation value calculating unit calculates a deviation value of the error data change trend coefficient and the normal data change trend coefficient; the difference feature extraction unit extracts a difference feature between the target data and the normal data based on the calculation result of the deviation value calculation unit.
The influence factor analysis and adjustment module comprises an influence factor analysis unit and an influence factor adjustment unit;
The influence factor analysis unit analyzes corresponding influence factors based on the difference characteristics between the target data and the normal data; and the influence factor adjusting unit adjusts the data value of the influence factor corresponding to the target data according to the influence factor corresponding to the difference characteristic.
The effect evaluation and feedback module comprises a simulation and comparison unit and a result feedback unit;
The simulation and comparison unit compares the adjusted product production qualification rate with the product production qualification rate before adjustment, and evaluates the dynamic adjustment effect of the production link; and the result feedback unit outputs the dynamic adjustment effect of all production links to related personnel, and prompts the related personnel to further process according to the comparison result.
A product error data analysis method based on programming production comprises the following steps:
S100, acquiring planning information of the whole production process of the product and production data of different batches of products, dividing the production data according to production links corresponding to the planning information, and forming a plurality of production link historical data sets;
Step S200, obtaining the production qualification rate of products in different batches, and evaluating the quality score of the production link for each element of the historical data set of all the production links; dividing the production data of the products corresponding to each batch into error data and normal data according to the quality scores of the production links, and analyzing the error data and the normal data of the same production links of different batches to obtain an error data change trend coefficient and a normal data change trend coefficient;
S300, analyzing the error data change trend coefficient and the normal data change trend coefficient, finding out influence factors related to the normal data change trend coefficient, and dynamically adjusting data values of the influence factors of the production links with error data with reference to the corresponding production links of the normal data;
S400, obtaining the adjusted product production qualification rate, comparing the adjusted product production qualification rate with the product production qualification rate before adjustment, judging the dynamic adjustment effect of the production links according to the comparison result, and outputting the dynamic adjustment effect of all the production links to related personnel for further processing by the related personnel.
Step S100 includes the following:
S101, planning information of the whole production process of the product refers to overall planning and design of the production process of the product, and the planning information comprises specific working contents, production standards and qualified product production data of a production link; the product production data refer to data collected in the production process of the product, including production process data, equipment operation data and quality control data; the production process data refer to process parameters used in various links in the production process, such as temperature, pressure, speed, time, proportion and the like; the equipment operation data refer to data related to the operation state of production equipment, including starting and stopping time of the equipment, working efficiency of the equipment and the like; the quality control data refers to quality inspection data such as product size, weight, composition, surface quality, appearance, etc. performed during or after the production process;
S102, acquiring planning information of the whole production process of the product and production data of different batches of products, and acquiring production links of the product according to the planning information of the whole production process of the product; based on the production links of the products, dividing the production data of different batches of products according to the different production links so as to form a plurality of production link history data sets Ai, wherein i represents the production link numbers, ai= { a1i, a2i, and ani }, wherein a1i represents the production data of the ith production link of the 1 st batch, a2i represents the production data of the ith production link of the 2 nd batch, and so on, ani represents the production data of the ith production link of the n-th batch, and n represents the batch times.
In this embodiment, it is assumed that the production process of one product includes three production links: step 1, step 2 and step 3, obtaining production data of three batches of products in a certain period of time, wherein the production data are respectively as follows:
batch 1: link 1, link 2, link 3;
batch 2: link 1, link 2, link 3;
batch 3: link 1, link 2, link 3;
thus, three production link history data sets Ai are formed, respectively:
a1 = { a11, a21, a31}, a2= { a12, a22, a32} and a3= { a13, a23, a33}.
Step S200 includes the following:
s201, obtaining product production qualification rates of different batches, and evaluating quality scores of production links for elements of each production link history data set by combining the production link history data set Ai and qualified product production data in planning information of the whole production process, wherein a specific calculation formula is as follows:
，
Wherein S ij represents the quality score of the ith production link of the jth batch, S ij represents the product production data of the ith production link of the jth batch, mu i represents the qualified product production data of the ith production link, sigma i represents the standard deviation of the product production data of the ith production link, and h j represents the product production qualification rate of the jth batch;
S202, obtaining quality scores of production links corresponding to elements of each production link historical data set, and respectively calculating quality score average values S0 of the production links for each production link historical data set; taking the element which is larger than or equal to the corresponding quality score average value S0 in each production link historical data set as normal data, and taking the element which is smaller than the corresponding quality score average value S0 in each production link historical data set as error data;
S203, respectively acquiring error data and normal data for each production link historical data set, so as to respectively calculate an error data change trend coefficient TC1 and a normal data change trend coefficient TC2, wherein the specific calculation formulas of the error data change trend coefficient and the normal data change trend coefficient are as follows:
，
Wherein TCb represents an error data change trend coefficient or a normal data change trend coefficient, b is 1 or 2, x k represents a value of the error data or the normal data at a kth time point, and m represents a time sequence length of the error data or the normal data.
The quality condition of each production link can be objectively evaluated by calculating the quality score of each production link and combining the historical data with the product production data; the calculation of the quality score combines the qualified product production data, the actual product production data and the standard deviation of the data, so that the stability and the accuracy in the product production process can be comprehensively considered; the quality level of each production link can be quantitatively reflected through the quality score, and guidance and reference are provided for optimizing the production process; elements in the historical data set are divided into error data and normal data, so that abnormal conditions in the production process can be recognized and distinguished; by calculating the change trend coefficients of the error data and the normal data, the change trend and regularity of the data can be analyzed.
Step S300 includes the following:
S301, respectively obtaining corresponding error data change trend coefficients TC1 and normal data change trend coefficients TC2 aiming at elements in each production link historical data set, and calculating deviation values R of the error data change trend coefficients TC1 and the normal data change trend coefficients TC2 of the same production link historical data set, wherein a specific calculation formula is as follows:
，
Wherein, TC2w represents the w-th normal data change trend coefficient in the same production link history data set, z represents the number of the normal data change trend coefficients in the same production link history data set, and TC20 represents the average value of the normal data change trend coefficients in the same production link history data set;
S302, acquiring a deviation value R of an error data change trend coefficient TC1 and a normal data change trend coefficient TC2 of the same production link historical data set aiming at each production link historical data set, and selecting error data with the largest deviation value R as target data; comparing target data with normal data in a historical data set of a production link one by one, so as to extract differential features between the target data and the normal data, thereby obtaining a differential feature set Bi, wherein Bi= { b1, b2, bv } i, bi represents the differential feature set of the ith production link, b1 represents the 1 st differential feature, b2 represents the 2 nd differential feature, and the like, bv represents the v differential feature, and v represents the number of differential features;
For each element in the differential feature set Bi, an influence factor corresponding to the differential feature is found, the data value of the influence factor corresponding to the target data is adjusted to the data value of the influence factor corresponding to the normal data according to the influence factor corresponding to the differential feature, and the adjusted data value of the influence factor corresponding to the target data is used as a simulation condition.
For finding out corresponding influencing factors according to the difference characteristics, the combination of some data analysis and domain knowledge is needed; firstly, carrying out detailed data analysis on the differential features, including statistical analysis, visual analysis and the like, so as to know the distribution, change rule and other conditions of the differential features; factors which may affect the differential features during the production process are known by the expert knowledge in the relevant field, and these factors may relate to various aspects of equipment, materials, processes, environment, etc., and may also help to identify the influencing factors related to the differential features by the expert or team.
Step S400 includes the following:
S401, regarding each production link historical data set, taking simulation conditions as initial conditions, acquiring target data, thus carrying out data simulation of corresponding production links of different batches, acquiring product simulation production data of different batches and corresponding product production qualification rate, and comparing the adjusted product production qualification rate with the product production qualification rate before adjustment;
s402, if the adjusted product production qualification rate is greater than the product production qualification rate before adjustment, storing an adjustment process; if the adjusted product production qualification rate is smaller than or equal to the product production qualification rate before adjustment, outputting prompt information to related personnel, further analyzing by the related personnel to enable the product production qualification rate after adjustment to be larger than the product production qualification rate before adjustment, and recording the analysis process of the related personnel.
For the data simulation of corresponding production links of different batches, firstly taking the data value of the influence factors corresponding to the adjusted target data as simulation conditions, including various parameters, equipment states, environmental factors and the like of the production links, wherein the conditions should cover various aspects which possibly influence the quality of products in the production process; selecting the most suitable simulation method according to actual conditions and requirements, thereby establishing a simulation model of a production link; the model can accurately reflect the interaction among all factors in the production process and the influence of the interaction on the product percent of pass; inputting the simulation conditions as initial conditions into a simulation model, and operating the simulation model to obtain simulation data; according to the set initial conditions and the simulation method, the production data of different batches of products and the corresponding product qualification rate are obtained.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, 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.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. A product error data analysis method based on programming production is characterized in that: the method comprises the following steps:
S100, acquiring planning information of the whole production process of the product and production data of different batches of products, dividing the production data according to production links corresponding to the planning information, and forming a plurality of production link historical data sets;
Step S200, obtaining the production qualification rate of products in different batches, and evaluating the quality score of the production link for each element of the historical data set of all the production links; dividing the production data of the products corresponding to each batch into error data and normal data according to the quality scores of the production links, and analyzing the error data and the normal data of the same production links of different batches to obtain an error data change trend coefficient and a normal data change trend coefficient;
The step S200 includes the following:
s201, obtaining product production qualification rates of different batches, and evaluating quality scores of production links for elements of each production link history data set by combining the production link history data set Ai and qualified product production data in planning information of the whole production process, wherein a specific calculation formula is as follows:
，
Wherein S ij represents the quality score of the ith production link of the jth batch, S ij represents the product production data of the ith production link of the jth batch, mu i represents the qualified product production data of the ith production link, sigma i represents the standard deviation of the product production data of the ith production link, and h j represents the product production qualification rate of the jth batch;
S202, obtaining quality scores of production links corresponding to elements of each production link historical data set, and respectively calculating quality score average values S0 of the production links for each production link historical data set; taking the element which is larger than or equal to the corresponding quality score average value S0 in each production link historical data set as normal data, and taking the element which is smaller than the corresponding quality score average value S0 in each production link historical data set as error data;
S203, respectively acquiring error data and normal data for each production link historical data set, so as to respectively calculate an error data change trend coefficient TC1 and a normal data change trend coefficient TC2, wherein the specific calculation formulas of the error data change trend coefficient and the normal data change trend coefficient are as follows:
，
wherein TCb represents the variation trend coefficient of the error data or the variation trend coefficient of the normal data, b is 1 or 2, x k represents the value of the error data or the normal data at the kth time point, and m represents the time sequence length of the error data or the normal data;
S300, analyzing the error data change trend coefficient and the normal data change trend coefficient, finding out influence factors related to the normal data change trend coefficient, and dynamically adjusting data values of the influence factors of the production links with error data with reference to the corresponding production links of the normal data;
the step S300 includes the following:
S301, respectively obtaining corresponding error data change trend coefficients TC1 and normal data change trend coefficients TC2 aiming at elements in each production link historical data set, and calculating deviation values R of the error data change trend coefficients TC1 and the normal data change trend coefficients TC2 of the same production link historical data set, wherein a specific calculation formula is as follows:
，
Wherein, TC2w represents the w-th normal data change trend coefficient in the same production link history data set, z represents the number of the normal data change trend coefficients in the same production link history data set, and TC20 represents the average value of the normal data change trend coefficients in the same production link history data set;
S302, acquiring a deviation value R of an error data change trend coefficient TC1 and a normal data change trend coefficient TC2 of the same production link historical data set aiming at each production link historical data set, and selecting error data with the largest deviation value R as target data; comparing target data with normal data in a historical data set of a production link one by one, so as to extract differential features between the target data and the normal data, thereby obtaining a differential feature set Bi, wherein Bi= { b1, b2, bv } i, bi represents the differential feature set of the ith production link, b1 represents the 1 st differential feature, b2 represents the 2 nd differential feature, and the like, bv represents the v differential feature, and v represents the number of differential features;
For each element in the differential feature set Bi, finding an influence factor corresponding to the differential feature, adjusting the data value of the influence factor corresponding to the target data into the data value of the influence factor corresponding to the normal data according to the influence factor corresponding to the differential feature, and taking the adjusted data value of the influence factor corresponding to the target data as a simulation condition;
S400, obtaining the adjusted product production qualification rate, comparing the adjusted product production qualification rate with the product production qualification rate before adjustment, judging the dynamic adjustment effect of the production links according to the comparison result, and outputting the dynamic adjustment effect of all the production links to related personnel for further processing by the related personnel.
2. A method for analyzing product error data based on planned production according to claim 1, wherein: the step S100 includes the following:
S101, planning information of the whole production process of the product refers to overall planning and design of the production process of the product, and the planning information comprises specific working contents, production standards and qualified product production data of a production link; the product production data refer to data collected in the production process of the product, including production process data, equipment operation data and quality control data;
S102, acquiring planning information of the whole production process of the product and production data of different batches of products, and acquiring production links of the product according to the planning information of the whole production process of the product; based on the production links of the products, dividing the production data of different batches of products according to the different production links so as to form a plurality of production link history data sets Ai, wherein i represents the production link numbers, ai= { a1i, a2i, and ani }, wherein a1i represents the production data of the ith production link of the 1 st batch, a2i represents the production data of the ith production link of the 2 nd batch, and so on, ani represents the production data of the ith production link of the n-th batch, and n represents the batch times.
3. A method for analyzing product error data based on planned production according to claim 1, wherein: the step S400 includes the following:
S401, regarding each production link historical data set, taking simulation conditions as initial conditions, acquiring target data, thus carrying out data simulation of corresponding production links of different batches, acquiring product simulation production data of different batches and corresponding product production qualification rate, and comparing the adjusted product production qualification rate with the product production qualification rate before adjustment;
s402, if the adjusted product production qualification rate is greater than the product production qualification rate before adjustment, storing an adjustment process; if the adjusted product production qualification rate is smaller than or equal to the product production qualification rate before adjustment, outputting prompt information to related personnel, further analyzing by the related personnel to enable the product production qualification rate after adjustment to be larger than the product production qualification rate before adjustment, and recording the analysis process of the related personnel.
4. A product error data analysis system based on programming production, which is applied to the product error data analysis method based on programming production as claimed in any one of claims 1 to 3, and is characterized in that: the system comprises: the device comprises a data acquisition module, a quality evaluation module, a trend analysis module, an influence factor analysis and adjustment module and an effect evaluation and feedback module;
The data acquisition module is responsible for acquiring planning information of the whole production process of the product and production data of different batches of products, dividing the production data according to production links corresponding to the planning information, and forming a plurality of production link historical data sets;
The quality evaluation module is used for carrying out quality evaluation on elements of each production link historical data set by combining the production link historical data set and qualified product production data in the planning information, evaluating quality scores of the production links and dividing error data and normal data;
The trend analysis module analyzes the change trend coefficients of the error data and the normal data, calculates the deviation value of the change trend coefficient of the error data and the change trend coefficient of the normal data, and extracts the difference characteristic;
the trend analysis module comprises a trend coefficient calculation unit, a deviation value calculation unit and a difference characteristic extraction unit;
The trend coefficient calculation unit analyzes error data and normal data of the same production links in different batches to obtain an error data change trend coefficient and a normal data change trend coefficient; the deviation value calculating unit calculates a deviation value of the error data change trend coefficient and the normal data change trend coefficient; the differential feature extraction unit extracts differential features between the target data and the normal data based on the calculation result of the deviation value calculation unit;
the influence factor analysis and adjustment module is used for identifying influence factors corresponding to the difference characteristics by analyzing the difference characteristics between the target data and the normal data; according to the influence factors corresponding to the difference characteristics, the data values of the influence factors corresponding to the target data are adjusted to the data values of the influence factors corresponding to the normal data;
the influence factor analysis and adjustment module comprises an influence factor analysis unit and an influence factor adjustment unit;
The influence factor analysis unit analyzes corresponding influence factors based on the difference characteristics between the target data and the normal data; the influence factor adjusting unit adjusts the data value of the influence factor corresponding to the target data according to the influence factor corresponding to the difference characteristic;
The effect evaluation and feedback module compares the adjusted product production qualification rate with the product production qualification rate before adjustment, judges the dynamic adjustment effect of the production links according to the comparison result, outputs the dynamic adjustment effect of all the production links to related personnel, and is further processed by the related personnel.
5. A product error data analysis system based on planned production as claimed in claim 4, wherein: the quality evaluation module comprises a production link dividing unit and a production link quality scoring unit;
The production link dividing unit divides the production data of the product according to the planning information and the production links to form a plurality of production link historical data sets; and the production link quality scoring unit is used for evaluating the quality scores of the production links for each element of all the production link historical data sets by combining the production qualification rates of the products in different batches.
6. A product error data analysis system based on planned production as claimed in claim 4, wherein: the effect evaluation and feedback module comprises a simulation and comparison unit and a result feedback unit;
the simulation and comparison unit compares the adjusted product production qualification rate with the product production qualification rate before adjustment, and evaluates the dynamic adjustment effect of the production link; and the result feedback unit outputs the dynamic adjustment effect of all production links to related personnel, and prompts the related personnel to further process according to the comparison result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410702523.4A CN118278825B (en) | 2024-06-03 | 2024-06-03 | Product error data analysis system and method based on planned production |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410702523.4A CN118278825B (en) | 2024-06-03 | 2024-06-03 | Product error data analysis system and method based on planned production |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118278825A CN118278825A (en) | 2024-07-02 |
| CN118278825B true CN118278825B (en) | 2024-09-27 |
Family
ID=91640322
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410702523.4A Active CN118278825B (en) | 2024-06-03 | 2024-06-03 | Product error data analysis system and method based on planned production |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118278825B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117314244A (en) * | 2023-10-07 | 2023-12-29 | 中节能（石家庄）环保能源有限公司 | Process flow data supervision system and method based on data analysis |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4417897B2 (en) * | 2005-09-14 | 2010-02-17 | 富士通マイクロエレクトロニクス株式会社 | Manufacturing data analyzing method and manufacturing data analyzing apparatus |
| US11054803B2 (en) * | 2018-07-13 | 2021-07-06 | Delta Electronics, Inc. | Motor drive, production system and method thereof with quality measuring and mechanism diagnosing functions using real and virtual system modules |
| CN117389236B (en) * | 2023-12-11 | 2024-02-13 | 山东三岳化工有限公司 | Propylene oxide production process optimization method and system |
-
2024
- 2024-06-03 CN CN202410702523.4A patent/CN118278825B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117314244A (en) * | 2023-10-07 | 2023-12-29 | 中节能（石家庄）环保能源有限公司 | Process flow data supervision system and method based on data analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118278825A (en) | 2024-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109840362B (en) | Multi-objective optimization-based integrated just-in-time learning industrial process soft measurement modeling method | |
| US20170315543A1 (en) | Evaluating petrochemical plant errors to determine equipment changes for optimized operations | |
| Guh | On‐line identification and quantification of mean shifts in bivariate processes using a neural network‐based approach | |
| CN108363836B (en) | Multi-working-condition self-adaptive industrial robot health degree assessment method and system | |
| TW201615844A (en) | Method and system of cause analysis and correction for manufacturing data | |
| CN112598172A (en) | Wind turbine bearing temperature early warning method | |
| CN109144986A (en) | A kind of importance appraisal procedure of industrial equipment data | |
| CN114326594A (en) | Machine tool performance evaluation system based on machine tool data and evaluation method thereof | |
| CN110928264A (en) | Data processing, data processing device, and computer-readable recording medium | |
| CN108197280B (en) | Mining ability evaluation method based on industrial equipment data | |
| CN117933822A (en) | Internet of things data management system and method based on edge calculation | |
| CN116028887A (en) | Analysis method of continuous industrial production data | |
| CN118244709A (en) | Associated fault equipment and influence factor acquisition method, device and exception handling system | |
| CN116934162A (en) | Agricultural machinery equipment operation management and control system based on data analysis | |
| CN117132064A (en) | Liquid crystal display produces line operation management system based on thing networking | |
| CN113934536B (en) | Data acquisition method facing edge calculation | |
| CN118278825B (en) | Product error data analysis system and method based on planned production | |
| CN112418682A (en) | Security assessment method fusing multi-source information | |
| CN112692875B (en) | Digital twin system for operation and maintenance of welding robot | |
| Sonmez et al. | Using accurately measured production amounts to obtain calibration curve corrections of production line speed and stoppage duration consisting of measurement errors | |
| CN115222307B (en) | Pipeline worker safety control method based on data analysis | |
| CN108985564B (en) | QFD (quad Flat No-lead) and binary semantic-based FMEA (failure mode and effects analysis) method | |
| CN117290795A (en) | Online identification method suitable for abnormal values of measurement results of single instrument | |
| CN115619280A (en) | Process quality prediction method based on process standard map and CNN-GRU network model | |
| CN116956720B (en) | Industrial digital twin simulation operation and maintenance system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 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 |