CN119579014A - A method and system for evaluating and predicting building material production quality based on data feedback - Google Patents
A method and system for evaluating and predicting building material production quality based on data feedback Download PDFInfo
- Publication number
- CN119579014A CN119579014A CN202510139857.XA CN202510139857A CN119579014A CN 119579014 A CN119579014 A CN 119579014A CN 202510139857 A CN202510139857 A CN 202510139857A CN 119579014 A CN119579014 A CN 119579014A
- Authority
- CN
- China
- Prior art keywords
- data
- production
- building materials
- performance defect
- performance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses a building material production quality evaluation prediction method and a system based on data feedback, which belong to the field of building material production, wherein the method comprises the steps of determining a production link of a building material according to the type of the building material and obtaining a production parameter data set; building materials with similar working conditions are selected, performance defect evaluation models based on production parameters of different production links are constructed, the performance defect evaluation models are trained to obtain optimal performance defect evaluation models, after each batch of building materials are produced, the corresponding optimal performance defect evaluation models are called according to the types of the possible performance defects, and production parameter data sets are input into the optimal performance defect evaluation models to predict performance defect data for building material quality evaluation and prediction. The system comprises a quality supervision feedback module, a production data acquisition module and a data analysis module. The method is suitable for the use scene of building materials under multiple working conditions, and provides a reliable data support and research method for the subsequent optimization of the performance of building materials and the improvement of the production process.
Description
Technical Field
The invention relates to the field of building material production, in particular to a building material production quality evaluation and prediction method and system based on data feedback.
Background
In the building material production process, the product quality is affected by various factors including raw material characteristics, production process parameters, production equipment states, environmental conditions and the like. The traditional quality control method often depends on sampling detection and post analysis, is difficult to master the quality change condition in the production process comprehensively in real time, can not effectively predict the future product quality trend, and timely improves and corrects the production process, so that the method can not adapt to the actual market demand. However, due to the variety of building materials and the wide variety of use conditions, various production processes exist for the same type of building materials, and in order to adapt to the variety of use conditions of the building materials, the production quality of the building materials is often not accurate enough from a single data angle. Therefore, there is a need for accurately assessing and predicting the quality of the building material in combination with defect feedback during use of the building material and uniformity of the use conditions.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a building material production quality evaluation prediction method and a system based on data feedback.
In order to achieve the aim of the invention, the invention adopts the following technical scheme:
the building material production quality evaluation prediction method based on data feedback comprises the following steps:
Step S1, determining production links of building materials according to the types of the building materials, and acquiring key production parameters of each production link affecting the quality of the building materials to obtain a production parameter data set:
;
wherein m is the number of the production link, Numbering the production parameters of the mth production link,The mth production linkA plurality of production parameters;
S2, utilizing performance defect data acquired by a quality supervision feedback module in the using process of the building materials, acquiring using condition data of the building materials, and screening building materials with similar using conditions from the building materials produced in the same batch;
Step S3, constructing performance defect evaluation models based on production parameters of different production links, training the performance defect evaluation models by utilizing historical performance defect data fed back in the using process of the building materials and the production parameters of the production links corresponding to the building materials, and optimizing the performance defect evaluation models based on new performance defect data to obtain an optimal performance defect evaluation model;
and S4, after each batch of building materials are produced, a corresponding optimal performance defect evaluation model is called according to the type of the possible performance defects, and the production parameter data set is input into the optimal performance defect evaluation model to predict the performance defect data for evaluating and predicting the production quality of the building materials.
Further, in the step S2, the building material screening method with similar working conditions is adopted;
S21, constructing a text database of building material using working condition types, splitting texts or vocabularies in the text database into single fonts, and establishing embedded data mapping of each font;
;
Where u is the font number, N is the number of strokes of the font, For the semantic classification labels of fonts, the semantic classification labels of fonts with the same semantics are the same,In order to embed the data mapping function,Embedded data for font u;
S22, each font obtains corresponding embedded data through embedded data mapping to obtain an initial embedded data set of the fonts in the text database;
S23, determining differences among embedded data according to the stroke number of the fonts and the semantic classification labels, constructing an embedded data difference function, and correcting the same embedded data in the initial embedded data set;
s24, obtaining a standard embedded data set after finishing the correction of the same embedded data in the initial embedded data set by utilizing an embedded data difference function;
step S25, according to the text combination of the building material using working condition type, calling the font embedded data combination corresponding to the text combination of the using working condition type from the standard embedded data set X is the font number of the working condition type text combination,Embedding data for the font of the working condition type text combination;
and S26, calculating similarity coefficients of the using working conditions of the building materials, evaluating the similarity of the using working conditions of the building materials by using the similarity coefficients, and screening the building materials with similar using working conditions.
Further, the embedded data difference function is:
;
Wherein, AndTwo font numbers which are identical to the embedded data in the initial embedded data set are respectively adopted,Respectively fontsAnd fontsIs used to determine the amount of embedded data,Respectively fontsAnd fontsIs used for the number of strokes of (a),Respectively fontsAnd fontsIs a semantic classification label of (c).
Further, step S26 includes:
step 261, calculating similarity coefficients of the using working conditions of the building materials;
;
Wherein, Is a term of semantic similarity to the term,For parameter similarity terms, i is the number of the font embedded data,Respectively embedding data for the ith font corresponding to the character combination of the using working condition type of the two building materials,The working condition parameters of the two building materials are respectively;
step S262 when When the parameters are similarAs a similarity coefficient to a set similarity thresholdComparing ifJudging that the working conditions of the two building materials are similar, otherwise, judging that the working conditions of the two building materials are dissimilar, whenAnd when the two building materials are used, the dissimilar use conditions of the two building materials are directly judged.
Further, step S3 includes:
Step S31, extracting performance defect data fed back by building materials with similar working conditions, and constructing a performance defect data set in the building materials with similar working conditions M is the kind of the performance defect data,Is the M-th performance defect data;
Step S32, constructing performance defect evaluation models based on production parameters of different production links ;
;
Wherein, The mth production linkProduction parametersCorresponding regression coefficients, performance defect assessment modelM performance defect evaluation submodels are built according to the number of production links;
step S33, generating a training data set by utilizing the historical performance defect data fed back in the using process of the building material and the production parameters of the production links corresponding to the building material, and evaluating a model for the performance defect Training, outputting an optimal regression coefficient, and obtaining a performance defect evaluation model after training;
Step S34, the quality supervision feedback module collects new performance defect dataCarrying the using condition data of the building materials, executing steps S21-S27 by using the using condition data, and calculating new performance defect dataCorresponding similarity coefficient of using working condition, and retrieving the training-completed performance defect evaluation model;
Step S35, new performance defect dataInput training completed performance defect evaluation model for production parameter data set of corresponding building materialOutputting m performance defect prediction data according to each performance defect evaluation submodel;
Step S36, calculating an average value of the performance defect prediction data;
;
Wherein, For the numbering of the performance defect prediction data,Is the firstPerformance defect prediction data;
step S37, calculating an average value And new performance defect dataDifference value and calculate the performance defect evaluation model after trainingPrecision coefficient of (a);
;
Step S38, setting a threshold value of the precision coefficient;
If it isThen the performance defect evaluation model with the current training completedThe precision meets the requirement, and the current optimal performance defect evaluation model is used, the step S34 is returned, and the quality supervision feedback module continues to collect new performance defect data;
If it is Then the performance defect evaluation model with the current training completedThe precision does not meet the requirement, and the process returns to the step S33 to process the new performance defect dataAs historical performance defect data, the training data set is updated, and the performance defect evaluation model is retrainedOutputting a new training finished performance defect evaluation modelAs a current optimal performance defect assessment model.
The building material production quality evaluation and prediction system executes the building material production quality evaluation and prediction method based on data feedback, and the system comprises the following steps:
The quality supervision feedback module comprises a performance data monitoring module, a data feedback module and an evaluation module;
The performance data monitoring module comprises a plurality of performance sensors arranged on the building materials and is used for collecting performance data in the use process of the building materials;
The data feedback module is used for inputting building material performance data fed back by staff;
the evaluation module is used for processing and screening the performance data and outputting performance defect data;
the production data acquisition module is used for acquiring key production parameters affecting the quality of building materials in each production link to obtain a production parameter data set;
And the data analysis module is used for carrying out data processing and analysis by combining the production parameter data set and the performance defect data, and evaluating and predicting the production quality of the building materials.
The invention has the beneficial effects that the performance defects in the using process of the building materials are screened by monitoring the performance change in the using process of the building materials and are used for reversely researching the defects in the producing process of the building materials, so that the invention can assist in optimizing the producing process and the process of the building materials under different using condition requirements. Meanwhile, the invention discusses the relation between the performance defects and production parameters of the building materials under the same working condition, builds an evaluation model, ensures the evaluation and prediction precision of the production quality defects of the building materials, adapts to the use scene of the building materials under multiple working conditions, reduces the influence of other factors on the production quality evaluation process, and provides a reliable data support and research method for the subsequent optimization of the performance of the building materials and the improvement of the production process.
Drawings
FIG. 1 is a flow chart of a method for building material production quality assessment prediction based on data feedback.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and all the inventions which make use of the inventive concept are protected by the spirit and scope of the present invention as defined and defined in the appended claims to those skilled in the art.
As shown in fig. 1, a building material production quality evaluation prediction method based on data feedback includes:
Step S1, determining production links of building materials according to the types of the building materials, and acquiring key production parameters of each production link affecting the quality of the building materials to obtain a production parameter data set:
;
wherein m is the number of the production link, Numbering the production parameters of the mth production link,The mth production linkAnd production parameters. The building materials are various in types, and the production links of different building materials are different, and the production process comprises mixing, stirring, forming, heat treatment and the like, and the production parameters comprise mixing and stirring time, stirring rotating speed, forming pressure, processing temperature and the like.
S2, utilizing performance defect data acquired by a quality supervision feedback module in the using process of the building materials, acquiring using condition data of the building materials, screening building materials with similar using conditions from the building materials produced in the same batch, wherein the using condition-similar building material screening method comprises the steps of bending deformation, insufficient strength, abnormal hardness, cracking, dimensional deviation, abnormal service life and the like of the building materials
S21, constructing a text database of building material using working condition types, splitting texts or vocabularies in the text database into single fonts, and establishing embedded data mapping of each font;
;
Where u is the font number, N is the number of strokes of the font, For the semantic classification labels of fonts, the semantic classification labels of fonts with the same semantics are the same,In order to embed the data mapping function,Embedded data for font u;
S22, each font obtains corresponding embedded data through embedded data mapping to obtain an initial embedded data set of the fonts in the text database;
Step S23, determining differences among embedded data according to the stroke number of the fonts and the semantic classification labels, constructing an embedded data difference function, and correcting the same embedded data in the initial embedded data set, wherein the embedded data difference function is as follows:
;
Wherein, AndTwo font numbers which are identical to the embedded data in the initial embedded data set are respectively adopted,Respectively fontsAnd fontsIs used to determine the amount of embedded data,Respectively fontsAnd fontsIs used for the number of strokes of (a),Respectively fontsAnd fontsIs a semantic classification label of (c).
The invention corrects accidental identical embedded data by introducing an embedded data difference function, thereby ensuring that one using condition type only corresponds to one embedded data.
S24, obtaining a standard embedded data set after finishing the correction of the same embedded data in the initial embedded data set by utilizing an embedded data difference function;
step S25, according to the text combination of the building material using working condition type, calling the font embedded data combination corresponding to the text combination of the using working condition type from the standard embedded data set X is the font number of the working condition type text combination,Embedding data for the font of the working condition type text combination;
and S26, calculating similarity coefficients of the using working conditions of the building materials, evaluating the similarity of the using working conditions of the building materials by using the similarity coefficients, and screening the building materials with similar using working conditions. The step S26 specifically includes:
step 261, calculating similarity coefficients of the using working conditions of the building materials;
;
Wherein, Is a term of semantic similarity to the term,For parameter similarity terms, i is the number of the font embedded data,Respectively embedding data for the ith font corresponding to the character combination of the using working condition type of the two building materials,The working condition parameters of the two building materials are respectively;
step S262 when When the parameters are similarAs a similarity coefficient to a set similarity thresholdComparing ifJudging that the working conditions of the two building materials are similar, otherwise, judging that the working conditions of the two building materials are dissimilar, whenAnd when the two building materials are used, the dissimilar use conditions of the two building materials are directly judged. Similarity thresholdRepresents the allowable maximum value of the similarity coefficient for judging the similarity of the used conditions.
And S3, constructing performance defect evaluation models based on production parameters of different production links, training the performance defect evaluation models by utilizing historical performance defect data fed back in the using process of the building materials and the production parameters of the production links corresponding to the building materials, and optimizing the performance defect evaluation models based on new performance defect data to obtain an optimal performance defect evaluation model. The step S3 specifically comprises the following steps:
Step S31, extracting performance defect data fed back by building materials with similar working conditions, and constructing a performance defect data set in the building materials with similar working conditions M is the kind of the performance defect data,Is the M-th performance defect data;
Step S32, constructing performance defect evaluation models based on production parameters of different production links ;
;
Wherein, The mth production linkProduction parametersCorresponding regression coefficients, performance defect assessment modelM performance defect evaluation submodels are built according to the number of production links;
step S33, generating a training data set by utilizing the historical performance defect data fed back in the using process of the building material and the production parameters of the production links corresponding to the building material, and evaluating a model for the performance defect Training, outputting an optimal regression coefficient, and obtaining a performance defect evaluation model after training;
Step S34, the quality supervision feedback module collects new performance defect dataCarrying the using condition data of the building materials, executing steps S21-S27 by using the using condition data, and calculating new performance defect dataCorresponding similarity coefficient of using working condition, and retrieving the training-completed performance defect evaluation model;
Step S35, new performance defect dataInput training completed performance defect evaluation model for production parameter data set of corresponding building materialOutputting m performance defect prediction data according to each performance defect evaluation submodel;
Step S36, calculating an average value of the performance defect prediction data;
;
Wherein, For the numbering of the performance defect prediction data,Is the firstPerformance defect prediction data;
step S37, calculating an average value And new performance defect dataDifference value and calculate the performance defect evaluation model after trainingPrecision coefficient of (a);
;
Step S38, setting a threshold value of the precision coefficientThreshold value ofThe accuracy coefficient representing the model accuracy meeting the requirements allows a maximum value.
If it isThen the performance defect evaluation model with the current training completedThe precision meets the requirement, and the current optimal performance defect evaluation model is used, the step S34 is returned, and the quality supervision feedback module continues to collect new performance defect data;
If it is Then the performance defect evaluation model with the current training completedThe precision does not meet the requirement, and the process returns to the step S33 to process the new performance defect dataAs historical performance defect data, the training data set is updated, and the performance defect evaluation model is retrainedOutputting a new training finished performance defect evaluation modelAs a current optimal performance defect assessment model.
And S4, after each batch of building materials are produced, a corresponding optimal performance defect evaluation model is called according to the type of the possible performance defects, and the production parameter data set is input into the optimal performance defect evaluation model to predict the performance defect data for evaluating and predicting the production quality of the building materials. In general, the larger the performance defect data calculated according to the optimal performance defect evaluation model, the poorer the performance of the produced building material under the condition of using the building material for drinking, and the poorer the quality of building material production.
A building material production quality evaluation and prediction system executes the building material production quality evaluation and prediction method based on data feedback, comprising the following steps:
The quality supervision feedback module comprises a performance data monitoring module, a data feedback module and an evaluation module;
The performance data monitoring module comprises a plurality of performance sensors arranged on the building materials and is used for collecting performance data in the use process of the building materials;
The data feedback module is used for inputting building material performance data fed back by staff;
the evaluation module is used for processing and screening the performance data and outputting performance defect data;
the production data acquisition module is used for acquiring key production parameters affecting the quality of building materials in each production link to obtain a production parameter data set;
And the data analysis module is used for carrying out data processing and analysis by combining the production parameter data set and the performance defect data, and evaluating and predicting the production quality of the building materials.
The invention screens the performance defects of the building materials in the using process by monitoring the performance change of the building materials in the using process, is used for reversely researching the defects of the building materials in the producing process, and can assist in optimizing the producing process and the producing process of the building materials under different using working condition requirements. Meanwhile, the invention discusses the relation between the performance defects and production parameters of the building materials under the same working condition, builds an evaluation model, ensures the evaluation and prediction precision of the production quality defects of the building materials, adapts to the use scene of the building materials under multiple working conditions, reduces the influence of other factors on the production quality evaluation process, and provides a reliable data support and research method for the subsequent optimization of the performance of the building materials and the improvement of the production process.
Claims (6)
1. The building material production quality evaluation prediction method based on data feedback is characterized by comprising the following steps of:
Step S1, determining production links of building materials according to the types of the building materials, and acquiring key production parameters of each production link affecting the quality of the building materials to obtain a production parameter data set:
;
wherein m is the number of the production link, Numbering the production parameters of the mth production link,The mth production linkA plurality of production parameters;
S2, utilizing performance defect data acquired by a quality supervision feedback module in the using process of the building materials, acquiring using condition data of the building materials, and screening building materials with similar using conditions from the building materials produced in the same batch;
Step S3, constructing performance defect evaluation models based on production parameters of different production links, training the performance defect evaluation models by utilizing historical performance defect data fed back in the using process of the building materials and the production parameters of the production links corresponding to the building materials, and optimizing the performance defect evaluation models based on new performance defect data to obtain an optimal performance defect evaluation model;
and S4, after each batch of building materials are produced, a corresponding optimal performance defect evaluation model is called according to the type of the possible performance defects, and the production parameter data set is input into the optimal performance defect evaluation model to predict the performance defect data for evaluating and predicting the production quality of the building materials.
2. The method for estimating and predicting the production quality of building materials based on data feedback according to claim 1, wherein the building material screening method using similar working conditions in the step S2 is as follows;
S21, constructing a text database of building material using working condition types, splitting texts or vocabularies in the text database into single fonts, and establishing embedded data mapping of each font;
;
Where u is the font number, N is the number of strokes of the font, For the semantic classification labels of fonts, the semantic classification labels of fonts with the same semantics are the same,In order to embed the data mapping function,Embedded data for font u;
S22, each font obtains corresponding embedded data through embedded data mapping to obtain an initial embedded data set of the fonts in the text database;
S23, determining differences among embedded data according to the stroke number of the fonts and the semantic classification labels, constructing an embedded data difference function, and correcting the same embedded data in the initial embedded data set;
s24, obtaining a standard embedded data set after finishing the correction of the same embedded data in the initial embedded data set by utilizing an embedded data difference function;
step S25, according to the text combination of the building material using working condition type, calling the font embedded data combination corresponding to the text combination of the using working condition type from the standard embedded data set X is the font number of the working condition type text combination,Embedding data for the font of the working condition type text combination;
and S26, calculating similarity coefficients of the using working conditions of the building materials, evaluating the similarity of the using working conditions of the building materials by using the similarity coefficients, and screening the building materials with similar using working conditions.
3. The method for estimating and predicting the production quality of building materials based on data feedback according to claim 2, wherein the embedded data difference function is:
;
Wherein, AndTwo font numbers which are identical to the embedded data in the initial embedded data set are respectively adopted,Respectively fontsAnd fontsIs used to determine the amount of embedded data,Respectively fontsAnd fontsIs used for the number of strokes of (a),Respectively fontsAnd fontsIs a semantic classification label of (c).
4. A method for predicting building material production quality based on data feedback as set forth in claim 3, wherein said step S26 includes:
step 261, calculating similarity coefficients of the using working conditions of the building materials;
;
Wherein, Is a term of semantic similarity to the term,For parameter similarity terms, i is the number of the font embedded data,Respectively embedding data for the ith font corresponding to the character combination of the using working condition type of the two building materials,The working condition parameters of the two building materials are respectively;
step S262 when When the parameters are similarAs a similarity coefficient to a set similarity thresholdComparing ifJudging that the working conditions of the two building materials are similar, otherwise, judging that the working conditions of the two building materials are dissimilar, whenAnd when the two building materials are used, the dissimilar use conditions of the two building materials are directly judged.
5. The method for estimating and predicting the production quality of building materials based on data feedback according to claim 4, wherein the step S3 comprises:
Step S31, extracting performance defect data fed back by building materials with similar working conditions, and constructing a performance defect data set in the building materials with similar working conditions M is the kind of the performance defect data,Is the M-th performance defect data;
Step S32, constructing performance defect evaluation models based on production parameters of different production links ;
;
Wherein, The mth production linkProduction parametersCorresponding regression coefficients, performance defect assessment modelM performance defect evaluation submodels are built according to the number of production links;
step S33, generating a training data set by utilizing the historical performance defect data fed back in the using process of the building material and the production parameters of the production links corresponding to the building material, and evaluating a model for the performance defect Training, outputting an optimal regression coefficient, and obtaining a performance defect evaluation model after training;
Step S34, the quality supervision feedback module collects new performance defect dataCarrying the using condition data of the building materials, executing steps S21-S27 by using the using condition data, and calculating new performance defect dataCorresponding similarity coefficient of using working condition, and retrieving the training-completed performance defect evaluation model;
Step S35, new performance defect dataInput training completed performance defect evaluation model for production parameter data set of corresponding building materialOutputting m performance defect prediction data according to each performance defect evaluation submodel;
Step S36, calculating an average value of the performance defect prediction data;
;
Wherein, For the numbering of the performance defect prediction data,Is the firstPerformance defect prediction data;
step S37, calculating an average value And new performance defect dataDifference value and calculate the performance defect evaluation model after trainingPrecision coefficient of (a);
;
Step S38, setting a threshold value of the precision coefficient;
If it isThen the performance defect evaluation model with the current training completedThe precision meets the requirement, and the current optimal performance defect evaluation model is used, the step S34 is returned, and the quality supervision feedback module continues to collect new performance defect data;
If it is Then the performance defect evaluation model with the current training completedThe precision does not meet the requirement, and the process returns to the step S33 to process the new performance defect dataAs historical performance defect data, the training data set is updated, and the performance defect evaluation model is retrainedOutputting a new training finished performance defect evaluation modelAs a current optimal performance defect assessment model.
6. A building material production quality evaluation prediction system that performs the data feedback-based building material production quality evaluation prediction method of any one of claims 1 to 5, comprising:
The quality supervision feedback module comprises a performance data monitoring module, a data feedback module and an evaluation module;
the performance data monitoring module comprises a plurality of performance sensors which are arranged on the building materials and are used for collecting performance data in the using process of the building materials;
The data feedback module is used for inputting building material performance data fed back by staff;
the evaluation module is used for processing and screening the performance data and outputting performance defect data;
the production data acquisition module is used for acquiring key production parameters affecting the quality of building materials in each production link to obtain a production parameter data set;
And the data analysis module is used for carrying out data processing and analysis by combining the production parameter data set and the performance defect data, and evaluating and predicting the production quality of the building materials.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510139857.XA CN119579014B (en) | 2025-02-08 | 2025-02-08 | Building material production quality assessment prediction method and system based on data feedback |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510139857.XA CN119579014B (en) | 2025-02-08 | 2025-02-08 | Building material production quality assessment prediction method and system based on data feedback |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119579014A true CN119579014A (en) | 2025-03-07 |
| CN119579014B CN119579014B (en) | 2025-04-18 |
Family
ID=94815764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510139857.XA Active CN119579014B (en) | 2025-02-08 | 2025-02-08 | Building material production quality assessment prediction method and system based on data feedback |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119579014B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020078403A1 (en) * | 2000-01-18 | 2002-06-20 | Gullo Louis J. | Reliability assessment and prediction system and method for implementing the same |
| US20210319265A1 (en) * | 2020-11-02 | 2021-10-14 | Zhengzhou University | Method for segmentation of underground drainage pipeline defects based on full convolutional neural network |
| WO2021220008A1 (en) * | 2020-04-29 | 2021-11-04 | Deep Render Ltd | Image compression and decoding, video compression and decoding: methods and systems |
| CN118037137A (en) * | 2024-04-11 | 2024-05-14 | 中国标准化研究院 | Method for determining product quality accident number based on convolutional neural network |
| WO2024103436A1 (en) * | 2022-11-18 | 2024-05-23 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Device defect data rule base construction method and device defect correlation analysis method |
| US20240320268A1 (en) * | 2023-03-23 | 2024-09-26 | Microsoft Technology Licensing, Llc | Theme based font search |
| CN118941395A (en) * | 2024-10-14 | 2024-11-12 | 中云开源数据技术（上海）有限公司 | An automatic generation and management system for data assets based on data operation technology |
| CN119228779A (en) * | 2024-10-15 | 2024-12-31 | 安徽中烟工业有限责任公司 | A method and system for detecting cigarette package appearance defects based on deep learning |
-
2025
- 2025-02-08 CN CN202510139857.XA patent/CN119579014B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020078403A1 (en) * | 2000-01-18 | 2002-06-20 | Gullo Louis J. | Reliability assessment and prediction system and method for implementing the same |
| WO2021220008A1 (en) * | 2020-04-29 | 2021-11-04 | Deep Render Ltd | Image compression and decoding, video compression and decoding: methods and systems |
| US20210319265A1 (en) * | 2020-11-02 | 2021-10-14 | Zhengzhou University | Method for segmentation of underground drainage pipeline defects based on full convolutional neural network |
| WO2024103436A1 (en) * | 2022-11-18 | 2024-05-23 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Device defect data rule base construction method and device defect correlation analysis method |
| US20240320268A1 (en) * | 2023-03-23 | 2024-09-26 | Microsoft Technology Licensing, Llc | Theme based font search |
| CN118037137A (en) * | 2024-04-11 | 2024-05-14 | 中国标准化研究院 | Method for determining product quality accident number based on convolutional neural network |
| CN118941395A (en) * | 2024-10-14 | 2024-11-12 | 中云开源数据技术（上海）有限公司 | An automatic generation and management system for data assets based on data operation technology |
| CN119228779A (en) * | 2024-10-15 | 2024-12-31 | 安徽中烟工业有限责任公司 | A method and system for detecting cigarette package appearance defects based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119579014B (en) | 2025-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117892583B (en) | Intelligent stamping control method and system | |
| CN110757510B (en) | A method and system for predicting the remaining life of a robot | |
| CN111105082A (en) | Workpiece quality prediction model construction method and prediction method based on machine learning | |
| CN119941726B (en) | A circuit board surface defect detection method and system | |
| CN117399435B (en) | Self-adaptive compensation adjustment method and system for copper pipe rolling process | |
| CN119972818B (en) | Method and system for dynamically regulating rolling of micro-stress of upper copper rod | |
| CN119830609B (en) | Rare earth extraction production flow simulation system and method | |
| CN117587403A (en) | Aluminum alloy template surface treatment method and system based on chemical conversion | |
| CN108470699B (en) | intelligent control system of semiconductor manufacturing equipment and process | |
| CN120124368A (en) | A mold 3D simulation analysis method | |
| CN119348221A (en) | A digital control method and system for online operation of multiple punching machines | |
| CN118403948B (en) | Optimized machining method and system for composite stamping die | |
| CN119579014B (en) | Building material production quality assessment prediction method and system based on data feedback | |
| CN118124106A (en) | Injection molding optimization control system and method based on neural network | |
| CN118364563B (en) | Aluminum white part stamping process for automobile body | |
| CN118047359B (en) | Control method and system for iron phosphate preparation equipment | |
| CN115877807B (en) | A mechanical chain production process control method and system based on machine recognition | |
| CN115293448A (en) | Method for calculating manufacturing energy consumption of single product in discrete manufacturing industry | |
| CN115527622A (en) | Method and system for monitoring reaction process of intermittent production resin | |
| CN120181685B (en) | Data annotation method and system for gold foil product testing | |
| CN117341261B (en) | Intelligent control method and system for servo direct-drive screw press | |
| CN119748797B (en) | A CNC compensation adjustment system for precision injection molds | |
| TWI824834B (en) | Roll forming process inspection method | |
| CN119517213B (en) | Machine learning-based steel pipe post-production mechanical property prediction method | |
| CN120688872A (en) | A quantitative analysis method for process parameter deviation risk |
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 |