CN113516285A - Product quality analysis and prediction method in production of automatic assembly detection production line - Google Patents
Product quality analysis and prediction method in production of automatic assembly detection production line Download PDFInfo
- Publication number
- CN113516285A CN113516285A CN202110518133.8A CN202110518133A CN113516285A CN 113516285 A CN113516285 A CN 113516285A CN 202110518133 A CN202110518133 A CN 202110518133A CN 113516285 A CN113516285 A CN 113516285A
- Authority
- CN
- China
- Prior art keywords
- quality
- station
- data
- product
- predicted
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 60
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000004458 analytical method Methods 0.000 title claims abstract description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 130
- 230000004927 fusion Effects 0.000 claims abstract description 73
- 238000007637 random forest analysis Methods 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000007689 inspection Methods 0.000 claims description 11
- 238000012417 linear regression Methods 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000010219 correlation analysis Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000012821 model calculation Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000011144 upstream manufacturing Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000012797 qualification Methods 0.000 abstract description 3
- 239000000047 product Substances 0.000 description 52
- 239000011265 semifinished product Substances 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
Images
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Educational Administration (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Quality & Reliability (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Manufacturing & Machinery (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses a product quality analysis and prediction method of an automatic assembly detection production line in production, which comprises the steps of collecting quality data of each production station (process) in the production line, preprocessing the collected data to form a quality data set, constructing sub-models of random forests, XGboost and LSTM algorithms, training an algorithm model by using the formed quality data set, and fusing and predicting by using a Stacking algorithm fusion technology. And applying a prediction model in actual production, and giving an early warning to workers through message pushing when quality problems occur. The quality of the product production process is analyzed and predicted in advance, so that the assembly production of the next station (process) is carried out under the condition that the quality of the previous station (process) meets the requirement, the loss of subsequent parts to be assembled is avoided, the utilization rate of the parts in the product assembly detection production process can be improved, unnecessary scrap is reduced practically, and the one-off-line qualification rate of the product production is improved.
Description
Technical Field
The invention relates to the technical field of automatic assembly, in particular to a product quality analysis and prediction method of an automatic assembly detection production line in production.
Background
On the automatic assembly detection production lines of a gas meter, a refrigerator compressor, an automobile door lock and the like, more than 10 assembly stations and detection stations are arranged on each automatic assembly detection production line. Therefore, the requirement on the matching precision of each station is high. When deviation occurs at one or more stations, the deviation cannot be found timely at the corresponding detection station or each station is near the detection upper limit and the detection lower limit, the deviation is judged to be qualified, the conditions of assembling semi-finished products or poor finished products and the like often occur, and the one-time offline qualification rate is low.
After the bad condition of the semi-finished product or the finished product occurs, the semi-finished product or the finished product is caused seriously, when the semi-finished product or the finished product is not serious, the semi-finished product or the finished product is generally required to be repaired, the repair is time-consuming and labor-consuming, and parts of subsequent assembly are easy to damage, so that the utilization rate of the parts in the product assembly detection production process is low.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a product quality analysis and prediction method for an automatic assembly detection production line in production, aiming at the defects of the prior art, the product quality analysis and prediction method for the automatic assembly detection production line in production uses a data acquisition technology to acquire quality data, uses a data preprocessing technology to process the acquired data to obtain a data set, uses machine learning and neural network to construct an algorithm model, and uses an algorithm fusion technology to fuse the model to complete the product quality analysis and prediction in the production process of the automatic assembly detection production line.
In order to solve the technical problems, the invention adopts the technical scheme that:
a product quality analysis and prediction method for an automatic assembly detection production line in production comprises the following steps.
Step 1, determining a prediction output station: the prediction output station is arranged at a repair station of the automatic assembly detection production line.
Step 2, predicting input station product marks: the method comprises the following steps that a product main body to be assembled is placed on a follow-up tool of an automatic assembly detection production line, an RFID chip is carried in each follow-up tool, and product information corresponding to the product main body to be assembled is arranged in each RFID chip.
Step 3, quality data acquisition: conveying the n following tools, in which the product main bodies to be assembled are placed, to a prediction output station from a feeding station of the product main bodies to be assembled after sequentially passing through each intermediate station; loading stations, each intermediate station and a prediction output station of a product main body to be assembled; the upper computer respectively reads the RFID chips in the accompanying tools and stores the quality detection data of each intermediate station and the prediction output station in the corresponding RFID chips; wherein n is more than or equal to 10.
Step 4, determining a predicted input station and key quality characteristics: performing data preprocessing on all the quality data acquired in the step 3, and determining a predicted input station and key quality characteristics; the prediction input station is arranged at a key station which is positioned at the upstream of the repair station and is used for controlling the quality of the repair station; the data preprocessing comprises data cleaning, quality feature extraction and correlation analysis; the key quality features are key features which influence the quality of the repair station in all quality data of the predicted input station.
And 5, constructing a quality data set: constructing a quality data set according to the predicted input station determined in the step 4 and all the quality data acquired in the step 3; the quality data set comprises a predicted input station quality data set and a predicted output station quality data set; the quality data set of the prediction input station comprises product information of n to-be-assembled product main bodies and key quality characteristic data of n groups of prediction input stations; the predicted output workstation quality data set comprises n groups of quality inspection data of the predicted output workstation.
And 6, constructing a Stacking fusion algorithm model, and specifically comprising the following steps.
And step 61, constructing three algorithm models: the three algorithm models comprise random forest, XGboost and LSTM algorithm models; randomly sampling from the quality data set of the prediction input station to be respectively used as input quantities of the three algorithm models, respectively using the quality data corresponding to the input quantities in the quality data set of the prediction output station as output quantities of the three algorithm models, and respectively training the three algorithm models until convergence; and further obtaining the random forest, XGboost and LSTM algorithm models.
Step 62, obtaining three types of model output data: respectively taking the whole quality data set of the prediction input station in the step 5 as input quantities in the random forest, XGboost and LSTM algorithm models constructed in the step 61, and further obtaining output data of the three models; the three model output data comprise predicted output station quality detection data of n groups of random forest algorithms, predicted output station quality detection data of n groups of XGboost algorithms and predicted output station quality detection data of n groups of LSTM algorithms.
Step 63, constructing a Stacking fusion algorithm model: taking the output data of the three models obtained in the step 62 as the input quantity of the Stacking fusion algorithm model, taking the quality detection data of the n groups of predicted output stations in the step 5 as the output quantity of the Stacking fusion algorithm model, and training the Stacking fusion algorithm model until convergence so as to obtain the required Stacking fusion algorithm model; the random forest algorithm model, the XGboost algorithm model, the LSTM algorithm model and the Stacking fusion algorithm model jointly form the Stacking fusion algorithm model, the input quantity of the Stacking fusion algorithm model is product information and key quality characteristic data of a predicted input station, and the output quantity of the Stacking fusion algorithm model is quality detection data of a predicted output station.
Step 7, analyzing and predicting product quality: after the follower tool containing the product to be analyzed and predicted is conveyed to the prediction output station from the feeding station, the upper computer reads the RFID chip in the corresponding follower tool to obtain the information of the product to be analyzed and predicted and the key quality characteristic data of the prediction input station, and the information and the key quality characteristic data are used as the input quantity of the Stacking fusion algorithm model to perform the Stacking fusion algorithm model calculation, so that the quality detection data of the product to be analyzed and predicted at the prediction output station are obtained.
In step 63, the construction process of the Stacking fusion algorithm model includes the following steps:
step 63A, weighted averaging: and carrying out weighted average on the output data of the three models input into the Stacking fusion algorithm model to form n groups of fused key quality characteristic data for predicting the input station.
Step 63B, linear regression: and taking the n groups of fused key quality characteristic data of the predicted input stations formed in the step 63A as fused input quantities in the Stacking fusion algorithm model, performing Stacking calculation to obtain n groups of Stacking fusion algorithm model output quantities containing undetermined coefficients, performing linear regression analysis on the Stacking fusion algorithm model output quantities containing undetermined coefficients and the n groups of quality detection data of the predicted output stations in the step 5, and solving to obtain undetermined coefficients in the Stacking fusion algorithm model so as to obtain the required Stacking fusion algorithm model.
In step 63A, when the three models are weighted and averaged, the weight value of each model is the accuracy of the corresponding model.
In step 61, in the process of constructing the random forest algorithm model and the XGboost algorithm model, parameter adjustment is carried out through a grid search method.
And each intermediate station and each prediction output station are provided with card readers connected with an upper computer and used for reading the RFID chip.
In the step 7, the upper computer can compare and judge the quality detection data of the output product to be analyzed and predicted at the predicted output station with preset quality data; when the product to be analyzed and predicted has quality problems, the upper computer can push the quality detection data of the product to be analyzed and predicted at the prediction output station and the comparison and judgment result to corresponding production line management personnel for early warning.
The automatic assembly detection production line is a gas meter, a refrigerator compressor or an automobile door lock.
In the step 6, the Stacking fusion algorithm model is a 5-fold Stacking fusion algorithm model.
The invention has the following beneficial effects:
1. the method comprises the steps of collecting quality data of each production station (process) in a production line, firstly, carrying out data cleaning, feature extraction, correlation analysis and other processing on the data by using a data preprocessing technology to form a quality data set, then, constructing sub models of random forests, XGboost and LSTM algorithms, training an algorithm model by using the formed quality data set, then, predicting by using 3 algorithm sub models by using a Stacking algorithm fusion technology, combining predicted data by using weighted average to form a new data set, training a linear regression model by using the new data set, and finally, completing fusion of the algorithm models. And applying a prediction model in actual production, and giving an early warning to workers through message pushing when quality problems occur.
2. The quality of the product production process is analyzed and predicted in advance, so that the assembly production of the next station (process) is carried out under the condition that the quality of the previous station (process) meets the requirement, the loss of subsequent parts to be assembled is avoided, the utilization rate of the parts in the product assembly detection production process can be improved, unnecessary scrap is reduced practically, and the one-off-line qualification rate of the product production is improved.
Drawings
FIG. 1 is a flow chart of a method for analyzing and predicting product quality during production in an automated assembly inspection line according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific preferred embodiments.
In the description of the present invention, it is to be understood that the terms "left side", "right side", "upper part", "lower part", etc., indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and that "first", "second", etc., do not represent an important degree of the component parts, and thus are not to be construed as limiting the present invention. The specific dimensions used in the present example are only for illustrating the technical solution and do not limit the scope of protection of the present invention.
As shown in FIG. 1, a method for predicting the quality of a product during production in an automatic assembly inspection production line comprises the following steps.
Step 1, determining a prediction output station: the predicted output station is arranged at a repair station of the automatic assembly detection production line; more preferably, the repair station has a high repair rate, and may be provided at each repair station.
The automatic assembly detection production line is preferably an automatic assembly detection production line such as a refrigerator compressor, a gas meter or an automobile door lock.
Step 2, predicting input station product marks: the method comprises the following steps that a product main body to be assembled is placed on a follow-up tool of an automatic assembly detection production line, an RFID chip is carried in each follow-up tool, and product information corresponding to the product main body to be assembled is arranged in each RFID chip.
Step 3, quality data acquisition
Conveying the n following tools, in which the product main bodies to be assembled are placed, to a prediction output station from a feeding station of the product main bodies to be assembled after sequentially passing through each intermediate station; at the loading station, each intermediate station and the prediction output station of the main body of the product to be assembled.
And each intermediate station and each prediction output station are provided with card readers connected with an upper computer and used for reading the RFID chip. The method is also a direct communication mode with the PLC, the data of each process device on the production line in the production process is collected in real time at high speed, and the collected data is stored in an upper computer without third-party software such as OPC (optical proximity correction) and the like, so that the communication is more stable and reliable. And collecting the assembly detection station in real time, and collecting quality result data of the product entering the repair station through an RFID chip.
The upper computer respectively reads the RFID chips in the accompanying tools and stores the quality detection data of each intermediate station and the prediction output station in the corresponding RFID chips; wherein n is more than or equal to 10.
Step 4, determining and predicting input stations and key quality characteristics
Performing data preprocessing such as data cleaning, quality feature extraction, correlation analysis and the like on all the quality data acquired in the step 3, and determining a prediction input station and key quality features; the prediction input station is arranged at a key station which is positioned at the upstream of the repair station and is used for controlling the quality of the repair station; the key quality features are key features which influence the quality of the repair station in all quality data of the predicted input station.
And 5, constructing a quality data set: constructing a quality data set according to the predicted input station determined in the step 4 and all the quality data acquired in the step 3; the quality data set comprises a predicted input station quality data set and a predicted output station quality data set; the quality data set of the prediction input station comprises product information of n to-be-assembled product main bodies and key quality characteristic data of n groups of prediction input stations; the predicted output workstation quality data set comprises n groups of quality inspection data of the predicted output workstation.
And 6, constructing a Stacking fusion algorithm model, and specifically comprising the following steps.
Step 61, constructing three algorithm models
The three algorithm models include random forest, XGboost and LSTM algorithm models.
Randomly sampling from the quality data set of the prediction input station to be respectively used as input quantities of the three algorithm models, respectively using the quality data corresponding to the input quantities in the quality data set of the prediction output station as output quantities of the three algorithm models, and respectively training the three algorithm models until convergence; and further obtaining the random forest, XGboost and LSTM algorithm models.
In the process of constructing the random forest algorithm model and the XGboost algorithm model, parameters are adjusted by a grid search method to obtain an optimal parameter combination, and the 3 models are used as a first-layer model for model fusion.
The random forest algorithm is an integrated algorithm model formed by combining a plurality of decision trees. The training data set of each decision tree is randomly sampled from the total quality data set, the training features are randomly sampled from the sample data set, and then each decision tree is trained.
The XGboost is an improved algorithm based on the GBDT algorithm. And L1 and L2 regularization terms are added in the XGboost algorithm, so that overfitting is reduced. The loss function is approximately calculated by using second-order Taylor expansion, so that the training speed of the model is accelerated.
The LSTM is a long-short term memory neural network, and is a special structural type of a recurrent neural network. By means of special structural elements: input gate, output gate and forget gate, extracting the previous information in a sequence and transmitting to the following neuron. Wherein, the forgetting door can effectively prevent the problem of information explosion.
Step 62, obtaining three types of model output data: respectively taking the whole quality data set of the prediction input station in the step 5 as input quantities in the random forest, XGboost and LSTM algorithm models constructed in the step 61, and further obtaining output data of the three models; the three model output data comprise predicted output station quality detection data of n groups of random forest algorithms, predicted output station quality detection data of n groups of XGboost algorithms and predicted output station quality detection data of n groups of LSTM algorithms.
Step 63, constructing a Stacking fusion algorithm model: and (3) taking the output data of the three models obtained in the step (62) as the input quantity of the Stacking fusion algorithm model, taking the quality detection data of the n groups of predicted output stations in the step (5) as the output quantity of the Stacking fusion algorithm model, and training the Stacking fusion algorithm model until convergence, thereby obtaining the required Stacking fusion algorithm model.
The random forest algorithm model, the XGboost algorithm model, the LSTM algorithm model and the Stacking fusion algorithm model jointly form the Stacking fusion algorithm model, the input quantity of the Stacking fusion algorithm model is product information and key quality characteristic data of a predicted input station, and the output quantity of the Stacking fusion algorithm model is quality detection data of a predicted output station.
The construction process of the Stacking fusion algorithm model preferably comprises the following steps:
step 63A, weighted averaging: and carrying out weighted average on the output data of the three models input into the Stacking fusion algorithm model to form n groups of fused key quality characteristic data for predicting the input station.
When the three models are weighted and averaged, the weighted value of each model is preferably the accuracy of the corresponding model.
Step 63B, linear regression: and taking the key quality characteristic data of the n groups of fused predicted input stations formed in the step 63A as the input quantity of the fused second layer in the Stacking fusion algorithm model, performing Stacking calculation to obtain n groups of Stacking fusion algorithm model output quantities containing undetermined coefficients, performing linear regression analysis on the Stacking fusion algorithm model output quantities containing undetermined coefficients and the quality detection data of the n groups of predicted output stations in the step 5, and solving to obtain undetermined coefficients in the Stacking fusion algorithm model so as to obtain the required Stacking fusion algorithm model.
The specific implementation method of the Stacking fusion algorithm model is as follows:
1. the quality data set is divided into a training set train and a test set test.
2. The training set train is divided into k subsets train _ C = { train _1, train _2, …, train _ k }, and the models to be fused are stored in the set and labeled as model _ C = { model _1, model _2, …, model _ n }.
3. And circulating the train _ C, wherein each subset train _ i (1< = i < = k) is used as a test set, and other subsets are combined to be used as a training set.
4. Model _ C is cycled, each submodel _ j (1< = j < = n) is taken, model _ j is trained and predicted using the generation training set and the test set in step 3, the prediction results are saved as { pred _1, pred _2, …, pred _ k }, and are combined into a new data set pred _ model _ j.
5. And (3) carrying out weighted average on all the pred _ model _ j data sets generated in the step 5 to obtain a new prediction result set pred.
6. And (3) constructing and training a fusion model by using the pred data set as a training set and the test as a prediction set, namely completing model fusion.
Further, the Stacking fusion algorithm model is preferably a 5-fold Stacking fusion algorithm model. Namely, the Stacking algorithm fusion and 5-fold cross validation technology are used simultaneously, the training data set is divided into 5 parts of sub data sets, 4 parts of the sub data sets are used as the training sets and 1 part of the sub data sets are used as the prediction sets each time, the cyclic training and the prediction are carried out, namely, each algorithm carries out prediction on the 5 parts of the sub data sets to obtain a complete prediction set, and then the 3 parts of the prediction sets are weighted and averaged according to the accuracy of random forests, XGBoost and LSTM models to be used as the training data set for the next layer of algorithm fusion.
Step 7, analyzing and predicting product quality: after the follower tool containing the product to be analyzed and predicted is conveyed to the prediction output station from the feeding station, the upper computer reads the RFID chip in the corresponding follower tool to obtain the information of the product to be analyzed and predicted and the key quality characteristic data of the prediction input station, and the information and the key quality characteristic data are used as the input quantity of the Stacking fusion algorithm model to perform the Stacking fusion algorithm model calculation, so that the quality detection data of the product to be analyzed and predicted at the prediction output station are obtained.
Then, the upper computer can compare and judge the quality detection data of the output product to be analyzed and predicted at the predicted output station with the preset quality data; when the product to be analyzed and predicted has quality problems, the upper computer can push the quality detection data of the product to be analyzed and predicted at the prediction output station and the comparison and judgment result to corresponding production line management personnel for early warning.
Although the preferred embodiments of the present invention have been described in detail, the present invention is not limited to the details of the embodiments, and various equivalent modifications can be made within the technical spirit of the present invention, and the scope of the present invention is also within the scope of the present invention.
Claims (8)
1. A product quality analysis and prediction method in production of an automatic assembly detection production line is characterized by comprising the following steps: the method comprises the following steps:
step 1, determining a prediction output station: the predicted output station is arranged at a repair station of the automatic assembly detection production line;
step 2, predicting input station product marks: placing a main body of a product to be assembled on the following tools of an automatic assembly detection production line, wherein each following tool carries an RFID chip, and the RFID chips are internally provided with product information corresponding to the main body of the product to be assembled;
step 3, quality data acquisition: conveying the n following tools, in which the product main bodies to be assembled are placed, to a prediction output station from a feeding station of the product main bodies to be assembled after sequentially passing through each intermediate station; respectively reading the RFID chips in the accompanying tool by the upper computer at a feeding station, each intermediate station and a prediction output station of a product main body to be assembled, and storing the quality detection data of each intermediate station and the prediction output station in the corresponding RFID chip; wherein n is more than or equal to 10;
step 4, determining a predicted input station and key quality characteristics: performing data preprocessing on all the quality data acquired in the step 3, and determining a predicted input station and key quality characteristics; the prediction input station is arranged at a key station which is positioned at the upstream of the repair station and is used for controlling the quality of the repair station; the data preprocessing comprises data cleaning, quality feature extraction and correlation analysis; the key quality characteristics are key characteristics which influence the quality of the repair station in all quality data of the predicted input station;
and 5, constructing a quality data set: constructing a quality data set according to the predicted input station determined in the step 4 and all the quality data acquired in the step 3; the quality data set comprises a predicted input station quality data set and a predicted output station quality data set; the quality data set of the prediction input station comprises product information of n to-be-assembled product main bodies and key quality characteristic data of n groups of prediction input stations; the quality data set of the predicted output stations comprises n groups of quality detection data of the predicted output stations;
step 6, constructing a Stacking fusion algorithm model, which specifically comprises the following steps:
and step 61, constructing three algorithm models: the three algorithm models comprise random forest, XGboost and LSTM algorithm models; randomly sampling from the quality data set of the prediction input station to be respectively used as input quantities of the three algorithm models, respectively using the quality data corresponding to the input quantities in the quality data set of the prediction output station as output quantities of the three algorithm models, and respectively training the three algorithm models until convergence; further obtaining the random forest, XGboost and LSTM algorithm models;
step 62, obtaining three types of model output data: respectively taking the whole quality data set of the prediction input station in the step 5 as input quantities in the random forest, XGboost and LSTM algorithm models constructed in the step 61, and further obtaining output data of the three models; the three model output data comprise predicted output station quality detection data of n groups of random forest algorithms, predicted output station quality detection data of n groups of XGboost algorithms and predicted output station quality detection data of n groups of LSTM algorithms;
step 63, constructing a Stacking fusion algorithm model: taking the output data of the three models obtained in the step 62 as the input quantity of the Stacking fusion algorithm model, taking the quality detection data of the n groups of predicted output stations in the step 5 as the output quantity of the Stacking fusion algorithm model, and training the Stacking fusion algorithm model until convergence so as to obtain the required Stacking fusion algorithm model; the method comprises the following steps that a random forest algorithm model, an XGboost algorithm model, an LSTM algorithm model and a Stacking fusion algorithm model jointly form the Stacking fusion algorithm model, the input quantity of the Stacking fusion algorithm model is product information and key quality characteristic data of a predicted input station, and the output quantity of the Stacking fusion algorithm model is quality detection data of a predicted output station;
step 7, analyzing and predicting product quality: after the follower tool containing the product to be analyzed and predicted is conveyed to the prediction output station from the feeding station, the upper computer reads the RFID chip in the corresponding follower tool to obtain the information of the product to be analyzed and predicted and the key quality characteristic data of the prediction input station, and the information and the key quality characteristic data are used as the input quantity of the Stacking fusion algorithm model to perform the Stacking fusion algorithm model calculation, so that the quality detection data of the product to be analyzed and predicted at the prediction output station are obtained.
2. The in-production product quality analysis prediction method for an automated assembly inspection line according to claim 1, characterized in that: in step 63, the construction process of the Stacking fusion algorithm model includes the following steps:
step 63A, weighted averaging: carrying out weighted average on the output data of the three models input into the Stacking fusion algorithm model to form n groups of fused key quality characteristic data of the prediction input station;
step 63B, linear regression: and taking the n groups of fused key quality characteristic data of the predicted input stations formed in the step 63A as fused input quantities in the Stacking fusion algorithm model, performing Stacking calculation to obtain n groups of Stacking fusion algorithm model output quantities containing undetermined coefficients, performing linear regression analysis on the Stacking fusion algorithm model output quantities containing undetermined coefficients and the n groups of quality detection data of the predicted output stations in the step 5, and solving to obtain undetermined coefficients in the Stacking fusion algorithm model so as to obtain the required Stacking fusion algorithm model.
3. The in-production product quality analysis prediction method for an automated assembly inspection line according to claim 2, characterized in that: in step 63A, when the three models are weighted and averaged, the weight value of each model is the accuracy of the corresponding model.
4. The in-production product quality analysis prediction method for an automated assembly inspection line according to claim 1, characterized in that: in step 61, in the process of constructing the random forest algorithm model and the XGboost algorithm model, parameter adjustment is carried out through a grid search method.
5. The in-production product quality analysis prediction method for an automated assembly inspection line according to claim 1, characterized in that: and each intermediate station and each prediction output station are provided with card readers connected with an upper computer and used for reading the RFID chip.
6. The in-production product quality analysis prediction method for an automated assembly inspection line according to claim 1, characterized in that: in the step 7, the upper computer can compare and judge the quality detection data of the output product to be analyzed and predicted at the predicted output station with preset quality data; when the product to be analyzed and predicted has quality problems, the upper computer can push the quality detection data of the product to be analyzed and predicted at the prediction output station and the comparison and judgment result to corresponding production line management personnel for early warning.
7. The in-production product quality analysis prediction method for an automated assembly inspection line according to claim 1, characterized in that: the automatic assembly detection production line is a gas meter, a refrigerator compressor or an automobile door lock.
8. The in-production product quality analysis prediction method for an automated assembly inspection line according to claim 1, characterized in that: in the step 6, the Stacking fusion algorithm model is a 5-fold Stacking fusion algorithm model.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110518133.8A CN113516285B (en) | 2021-05-12 | 2021-05-12 | Product quality analysis and prediction method of automatic assembly detection production line in production |
| PCT/CN2021/130621 WO2022237105A1 (en) | 2021-05-12 | 2021-11-15 | Quality analysis and prediction method for product during production of automatic assembly and detection production line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110518133.8A CN113516285B (en) | 2021-05-12 | 2021-05-12 | Product quality analysis and prediction method of automatic assembly detection production line in production |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113516285A true CN113516285A (en) | 2021-10-19 |
| CN113516285B CN113516285B (en) | 2024-02-13 |
Family
ID=78064228
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110518133.8A Active CN113516285B (en) | 2021-05-12 | 2021-05-12 | Product quality analysis and prediction method of automatic assembly detection production line in production |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113516285B (en) |
| WO (1) | WO2022237105A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113655768A (en) * | 2021-10-21 | 2021-11-16 | 深圳市信润富联数字科技有限公司 | Assembly yield control method, equipment and computer readable storage medium |
| WO2022237105A1 (en) * | 2021-05-12 | 2022-11-17 | 中船重工鹏力（南京）智能装备系统有限公司 | Quality analysis and prediction method for product during production of automatic assembly and detection production line |
| CN115511367A (en) * | 2022-10-21 | 2022-12-23 | 上海数瞳信息科技有限公司 | Intelligent quality management system of production line |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116119284B (en) * | 2022-12-16 | 2023-11-24 | 工业富联(杭州)数据科技有限公司 | Material assembling method, device, equipment and medium based on artificial intelligence |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106845796A (en) * | 2016-12-28 | 2017-06-13 | 中南大学 | One kind is hydrocracked flow product quality on-line prediction method |
| CN109348497A (en) * | 2018-09-30 | 2019-02-15 | 南昌航空大学 | Wireless sensor network link quality prediction method |
| CN109472057A (en) * | 2018-10-16 | 2019-03-15 | 浙江大学 | Based on product processing quality prediction meanss and method across the implicit parameters memorizing of work step |
| CN109711714A (en) * | 2018-12-24 | 2019-05-03 | 浙江大学 | Product quality prediction technique is assembled in manufacture based on shot and long term memory network in parallel |
| CN110288199A (en) * | 2019-05-29 | 2019-09-27 | 北京航空航天大学 | The method of product quality forecast |
| CN111814385A (en) * | 2020-05-28 | 2020-10-23 | 平安科技（深圳）有限公司 | Method, device and computer equipment for predicting quality of workpiece |
| CN112463643A (en) * | 2020-12-16 | 2021-03-09 | 郑州航空工业管理学院 | Software quality prediction method |
| US20210132593A1 (en) * | 2019-11-06 | 2021-05-06 | Nanotronics Imaging, Inc. | Systems, Methods, and Media for Manufacturing Processes |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI267012B (en) * | 2004-06-03 | 2006-11-21 | Univ Nat Cheng Kung | Quality prognostics system and method for manufacturing processes |
| US10902368B2 (en) * | 2014-03-12 | 2021-01-26 | Dt360 Inc. | Intelligent decision synchronization in real time for both discrete and continuous process industries |
| CN111461555B (en) * | 2020-04-02 | 2023-06-09 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Production line quality monitoring method, device and system |
| CN113516285B (en) * | 2021-05-12 | 2024-02-13 | 中船重工鹏力（南京）智能装备系统有限公司 | Product quality analysis and prediction method of automatic assembly detection production line in production |
-
2021
- 2021-05-12 CN CN202110518133.8A patent/CN113516285B/en active Active
- 2021-11-15 WO PCT/CN2021/130621 patent/WO2022237105A1/en active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106845796A (en) * | 2016-12-28 | 2017-06-13 | 中南大学 | One kind is hydrocracked flow product quality on-line prediction method |
| CN109348497A (en) * | 2018-09-30 | 2019-02-15 | 南昌航空大学 | Wireless sensor network link quality prediction method |
| CN109472057A (en) * | 2018-10-16 | 2019-03-15 | 浙江大学 | Based on product processing quality prediction meanss and method across the implicit parameters memorizing of work step |
| CN109711714A (en) * | 2018-12-24 | 2019-05-03 | 浙江大学 | Product quality prediction technique is assembled in manufacture based on shot and long term memory network in parallel |
| CN110288199A (en) * | 2019-05-29 | 2019-09-27 | 北京航空航天大学 | The method of product quality forecast |
| US20210132593A1 (en) * | 2019-11-06 | 2021-05-06 | Nanotronics Imaging, Inc. | Systems, Methods, and Media for Manufacturing Processes |
| CN111814385A (en) * | 2020-05-28 | 2020-10-23 | 平安科技（深圳）有限公司 | Method, device and computer equipment for predicting quality of workpiece |
| CN112463643A (en) * | 2020-12-16 | 2021-03-09 | 郑州航空工业管理学院 | Software quality prediction method |
Non-Patent Citations (2)
| Title |
|---|
| 景熠;王旭;李文川;: "基于RFID的变速器装配线质量追溯系统研究", 现代科学仪器, no. 05, 15 October 2011 (2011-10-15) * |
| 陈海;: "基于RFID优化发动机装配过程质量控制", 装备制造技术, no. 10, 15 October 2016 (2016-10-15) * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022237105A1 (en) * | 2021-05-12 | 2022-11-17 | 中船重工鹏力（南京）智能装备系统有限公司 | Quality analysis and prediction method for product during production of automatic assembly and detection production line |
| CN113655768A (en) * | 2021-10-21 | 2021-11-16 | 深圳市信润富联数字科技有限公司 | Assembly yield control method, equipment and computer readable storage medium |
| CN115511367A (en) * | 2022-10-21 | 2022-12-23 | 上海数瞳信息科技有限公司 | Intelligent quality management system of production line |
| CN115511367B (en) * | 2022-10-21 | 2023-07-25 | 上海数瞳信息科技有限公司 | Intelligent quality management system of production line |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113516285B (en) | 2024-02-13 |
| WO2022237105A1 (en) | 2022-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113516285A (en) | Product quality analysis and prediction method in production of automatic assembly detection production line | |
| US20220137612A1 (en) | Transformer fault diagnosis and positioning system based on digital twin | |
| CN112765768B (en) | Discrete workshop digital traceability method based on Internet of things | |
| CN112508053A (en) | Intelligent diagnosis method, device, equipment and medium based on integrated learning framework | |
| CN107220734A (en) | CNC Lathe Turning process Energy Consumption Prediction System based on decision tree | |
| CN105677791B (en) | For analyzing the method and system of the operation data of wind power generating set | |
| CN113702895B (en) | Online quantitative evaluation method for error state of voltage transformer | |
| CN111069819A (en) | Welding quality prediction system and method based on artificial intelligence | |
| CN105759784A (en) | Fault diagnosis method based on data envelopment analysis | |
| CN115994046B (en) | High-precision identification method and system for equipment inspection | |
| CN111898673A (en) | Dissolved oxygen content prediction method based on EMD and LSTM | |
| CN112419268A (en) | Method, device, equipment and medium for detecting image defects of power transmission line | |
| CN114548494A (en) | Visual cost data prediction intelligent analysis system | |
| CN108380527B (en) | Battery batch sorting system and method | |
| CN111026060A (en) | Digital intelligent manufacturing system for high-performance mechanical basic components | |
| CN111967501B (en) | Method and system for judging load state driven by telemetering original data | |
| CN113989550A (en) | Electric vehicle charging pile operation state prediction method based on CNN and LSTM hybrid network | |
| CN108363738B (en) | Recommendation method for industrial equipment data analysis algorithm | |
| CN111330871A (en) | Quality classification method and device | |
| CN115938009A (en) | Intelligent electronic patrol positioning method and system | |
| CN115115213A (en) | Method and device for retrospective analysis of quality characteristics of steel products | |
| Sun et al. | An automated warehouse sorting system for small manufacturing enterprise applying discrete event simulation | |
| CN114545276A (en) | Power battery service life prediction method based on capacity test and Internet of vehicles big data | |
| CN114626482A (en) | Active digital array radar real-time fault diagnosis method based on deep learning | |
| CN113689036A (en) | Thermal imager quality problem reason prediction method based on decision tree C4.5 algorithm |
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 |