CN107391890B - Prediction and optimal control method for oil casing threaded joint machining chatter defect - Google Patents
Prediction and optimal control method for oil casing threaded joint machining chatter defect Download PDFInfo
- Publication number
- CN107391890B CN107391890B CN201710780169.7A CN201710780169A CN107391890B CN 107391890 B CN107391890 B CN 107391890B CN 201710780169 A CN201710780169 A CN 201710780169A CN 107391890 B CN107391890 B CN 107391890B
- Authority
- CN
- China
- Prior art keywords
- chatter
- data
- prediction
- chatter mark
- machining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003754 machining Methods 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000007547 defect Effects 0.000 title claims abstract description 16
- 238000005457 optimization Methods 0.000 claims abstract description 38
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 23
- 238000007418 data mining Methods 0.000 claims abstract description 19
- 238000013461 design Methods 0.000 claims abstract description 15
- 230000002068 genetic effect Effects 0.000 claims abstract description 14
- 238000003064 k means clustering Methods 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000004519 manufacturing process Methods 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 20
- 238000012795 verification Methods 0.000 claims description 12
- 230000004044 response Effects 0.000 claims description 9
- 229910000831 Steel Inorganic materials 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 239000010959 steel Substances 0.000 claims description 8
- 239000013598 vector Substances 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000000342 Monte Carlo simulation Methods 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 5
- 238000007667 floating Methods 0.000 claims description 5
- 238000009434 installation Methods 0.000 claims description 5
- 206010061592 cardiac fibrillation Diseases 0.000 claims description 4
- 230000001419 dependent effect Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 230000002600 fibrillogenic effect Effects 0.000 claims description 4
- 230000035945 sensitivity Effects 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 2
- 239000003208 petroleum Substances 0.000 abstract description 2
- 239000000725 suspension Substances 0.000 description 5
- 238000007789 sealing Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000001050 lubricating effect Effects 0.000 description 2
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/18—Manufacturability analysis or optimisation for manufacturability
-
- 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
Abstract
The invention discloses a prediction and optimization control method for chatter mark defects in machining of an oil casing threaded joint, and relates to the technical field of petroleum equipment manufacturing, aiming at the rules and characteristics of chatter mark generation in the machining of threads, based on actual large data of chatter mark generation conditions, data mining, reliability analysis and optimization design theoretical methods are alternately applied, especially, an improved K-means clustering algorithm is adopted to implement data mining, an improved non-dominated sorting genetic algorithm is adopted to implement chatter mark defect control optimization, and a prediction and optimization control method for chatter mark defects in machining of the oil casing threaded joint is provided; compared with the prior art, the prediction and optimal control method for the oil casing threaded joint machining chatter defects can improve the accuracy of oil casing threaded joint machining chatter prediction and effectively control chatter.
Description
Technical Field
The invention relates to the technical field of petroleum equipment manufacturing, in particular to a prediction and optimization control method for chatter mark defects in machining of an oil casing threaded joint.
Background
The oil-gas well pipe column is formed by connecting a large number of oil casing single pipes through threads, and the number of the oil casing threads of the oil-gas single well is many thousands of times. The thread is an important link for guaranteeing the service structure and the sealing integrity of the pipe column under the composite load states of underground stretching, compression, bending, torsion, internal/external pressure and the like, and is also the weakest link (according to incomplete statistics, about 70% of failures of the structure and the sealing integrity of the underground pipe column occur in the thread part). The harsh service environment and the extremely high safe reliability index of the thread put high requirements on thread galling resistance, connection performance and sealing performance, and the machining precision and quality of the thread are very important.
Chatter is a phenomenon commonly existing in the production and processing processes of special threaded joints, not only affects the surface quality of the special threaded joints, but also causes various performances of the special threaded joints to deteriorate, directly reduces the use performance of threads, and particularly has remarkable effects on thread galling resistance and sealing performance. The occurrence of chatter marks is influenced by a complex coupling of factors, including: the pipe body suspension length, the inner support and the floating support roller are related to the pipe sample rigidity; cutter bar diameter and overhang length related to cutter rigidity, bearing clearance and bearing lubricity data related to lathe rigidity; clamping pressure, jaw size and clamping contact area related to a pipe sample clamping mode; the clearance between the blade and the shim, the clamping tightness and the distance between the tool tip and the center of the lathe are related to the quality and the installation of the tool; depth of cut, feed, etc. associated with the machining process. In the prior art, repeated adjustment and optimization are often performed through process trial and error, so that the reason for generating chatter marks in engineering practice is difficult to find, and evasive measures are lacked. Aiming at the rule and the characteristic of the chatter marks generated during the thread machining, the invention provides a prediction and optimization control method for the chatter mark defects generated during the machining of the oil casing threaded joint by alternately applying data mining, reliability analysis and optimization design theoretical methods based on actual chatter mark generation condition big data.
Disclosure of Invention
The invention aims to provide a prediction and optimization control method for chatter mark defects in machining of an oil casing threaded joint, so that accuracy of chatter mark generation prediction is improved, and chatter mark generation is effectively controlled.
The technical scheme adopted by the invention for solving the technical problems is as follows: a prediction and optimization control method for oil casing threaded joint machining chatter mark defects is characterized in that a plurality of groups of thread machining process parameters of different steel grades, specifications and thread types and corresponding actual chatter mark data of a thread surface are prestored in an original database; the processing technological parameter data comprises pipe body overhang length, an inner support and a floating support roller related to pipe sample rigidity, cutter bar diameter and overhang length related to cutter rigidity, bearing clearance and bearing lubricity data related to lathe rigidity, clamping pressure, jaw size and clamping contact area related to a pipe sample clamping mode, blade and tool pad clearance related to cutter quality and installation, clamping tightness and the distance between a cutter point and the center of a lathe; depth of cut, feed, etc. associated with the machining process; the actual chatter mark data of the thread surface comprises rating data for observing and detecting the severity of chatter marks on the actually machined thread surface; the method comprises the following steps:
s1, selecting at least two groups of oil casing thread machining process parameter data with the same specification, steel grade and thread type and corresponding thread actual surface chatter mark data stored in an original database, normalizing and abstracting the selected data into vectors, dividing the normalized and quantized data into training data samples and verification data samples, and respectively placing the training data samples and the verification data samples into a training sample library and a verification sample library;
s2, carrying out data mining modeling on the training data sample by adopting an improved K-means clustering algorithm to obtain a chatter mark production prediction model based on data mining for oil casing thread machining, wherein machining process parameters are used as dependent variables, and chatter mark data on the surface of threads are used as response variables;
s3, verifying the correctness of the prediction model based on the data mining for the fibrillation production by using the test data sample, if the test is passed, obtaining a fibrillation prediction expert model, executing S4, otherwise, transposing S1, and selecting updated data to execute the process repeatedly;
s4, predicting the chatter mark generation degree under the specified process condition input by the user by adopting the obtained chatter mark prediction expert model, and outputting a chatter mark prediction result;
s5, analyzing and obtaining a process parameter distribution model according to a large number of actually measured machining process parameters in the training sample library, and establishing a reliability prediction model of the chatter marks based on the response surface function through Monte Carlo simulation by combining the chatter mark prediction expert model established in S4;
s6, determining the designed target reliability through comprehensive analysis of rejection rate requirement analysis and cost control requirement analysis of thread machining, checking the target reliability as a standard, taking the comparison difference between the chatter mark reliability and the target reliability in the chatter mark reliability prediction model obtained through calculation of S5 as a target function, taking machining process parameters as design variables, performing reliability optimization iteration by using an improved non-dominated sorting genetic algorithm, finally meeting the requirement of the target reliability, and outputting a process parameter optimization design result for controlling chatter marks.
In the step S2, data mining modeling is implemented according to the principle of a K-means clustering algorithm, and the data mining modeling steps are as follows:
(1) randomly selecting k objects from n process parameter mathematical vectors actually forming the chatter marks as initial cluster centers;
(2) calculating the distance between each object and the centers of the clusters according to the mean values of the objects in the clusters, and assigning each object to the most similar cluster;
(3) updating the cluster mean value, namely calculating the mean value of the objects in each cluster;
(4) looping (2) and (3) until each cluster criterion function no longer changes;
and completing the prediction of a plurality of process parameters generated by forming the chatter marks.
As optimization, the K-means clustering algorithm is based on the principle of selecting K points with the batch distance as far as possible as an initial cluster, firstly randomly selecting one point as a first initial cluster center point, then selecting the point farthest from the point as a second initial cluster center point, then selecting the point with the closest distance to the first two points as a third initial cluster center point, and so on until K objects are selected as the initial cluster centers.
The reliability prediction model of the chatter marks utilizes an improved non-dominated sorting genetic algorithm to carry out optimization iteration, the reliability optimization iteration adopts the optimization design of the non-dominated sorting genetic algorithm, the optimization iteration process including genetic code generation, random initial population determination, fitness evaluation and offspring population calculation is implemented, on the basis of evaluating Pareto sorting values of individuals, the sensitivity of optimization target nearness to population density information around the individuals is evaluated by introducing the mean value and standard deviation of individual variables and sorting values thereof, and the next generation inheritance of the individuals is far away from the region where the population is inactive.
The invention has the beneficial effects that: establishing a chatter mark prediction model based on data mining by an improved K-means method based on actually detected thread machining process parameter data and corresponding actually generated chatter mark data during thread machining, and predicting the generation degree of chatter marks under the condition of preset process parameters according to the model; combining with statistics of thread machining process parameter distribution data, establishing a chatter mark reliability prediction model through Monte Carlo simulation, establishing an expected chatter mark reliability index according to consideration of quality and cost, adopting an improved non-dominated sorting genetic algorithm, performing optimization calculation by taking the expected chatter mark reliability index as an optimization target and taking thread machining process parameters as optimization design parameters, and obtaining a machining process parameter optimization result for controlling chatter mark generation. Therefore, the accuracy of the chatter mark generation prediction can be improved, and the chatter mark generation probability can be effectively controlled.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of a control method of the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
A prediction and optimization control method for chatter mark defects in machining of an oil casing threaded joint mainly comprises the following steps:
1. a user establishes an oil sleeve thread machining chatter actual condition database, and inputs, continuously accumulates, updates and stores a plurality of groups of thread machining process parameters of different steel grades, specifications and thread types and corresponding thread surface actual chatter data in the database; the processing technology parameter data comprises: the pipe body suspension length, the inner support and the floating support roller related to the rigidity of the pipe sample, the cutter bar diameter and the suspension length related to the rigidity of a cutter, the bearing clearance related to the rigidity of a lathe and bearing lubricating data; clamping pressure, jaw size and clamping contact area related to a pipe sample clamping mode; the clearance between the blade and the shim, the clamping tightness and the distance between the tool tip and the center of the lathe are related to the quality and the installation of the tool; depth of cut, feed, etc. associated with the machining process. Actual chatter data for a threaded surface, comprising: and (4) rating data for observing and detecting the severity of chatter marks on the surface of the actually machined thread.
2. At least two groups of oil casing thread machining process parameter data with the same specification, steel grade and thread type and corresponding thread actual surface chatter mark data stored in an original database are normalized and abstracted into vectors, the normalized data are divided into training data samples and verification data samples, and the training data samples and the verification data samples are respectively placed into a training sample library and a verification sample library.
3. And carrying out data mining modeling on the training data sample by adopting an improved K-means clustering algorithm to obtain a chatter mark production prediction model based on data mining for oil sleeve thread machining, wherein machining process parameters are used as dependent variables, and chatter mark data on the surface of the thread are used as response variables.
Further, chatter marks are affected by the complex coupling of the above-mentioned multidimensional data, and it is difficult to determine the intrinsic mechanism. And (3) implementing data mining modeling according to the principle of a K-means clustering algorithm:
(1) randomly selecting k objects from n process parameter mathematical vectors actually forming the chatter marks as initial cluster centers;
(2) calculating the distance between each object and the centers of the clusters according to the mean values of the objects in the clusters, and assigning each object to the most similar cluster;
(3) updating the cluster mean value, namely calculating the mean value of the objects in each cluster;
(4) looping (2) and (3) until each cluster criterion function no longer changes;
therefore, the prediction of a plurality of process parameters for forming the chatter marks is completed;
further, the improvement of the K-means clustering algorithm comprises the following steps: the K-means clustering algorithm is particularly sensitive to the initial value and the selected number of the initial cluster centers, and the improvement is provided aiming at the problem: based on the principle of selecting K points with the batch distance as far as possible as the initial cluster, firstly, randomly selecting one point as the center point of the first initial cluster, then selecting the point with the distance from the point to the farthest as the center point of the second initial cluster, then selecting the point with the distance from the two points to the nearest to the first point to the farthest as the center point of the third initial cluster, and so on until K objects are selected as the centers of the initial clusters.
4. And verifying the correctness of the chatter mark production prediction model based on data mining by using the inspection data sample, if the chatter mark prediction expert model is obtained after the inspection is passed, executing chatter mark prediction, predicting chatter mark production degree under specified process conditions, and outputting a prediction result, otherwise, transposing an original database of the oil casing thread machining chatter mark actual condition, and selecting an updated database to execute the flow repeatedly.
5. And analyzing and acquiring a process parameter distribution model according to a large number of actually measured machining process parameters in the training sample library, and establishing a reliability prediction model of the chatter marks based on the response surface function through Monte Carlo simulation by combining the established chatter mark prediction expert model.
6. And determining the target reliability of the design through comprehensive analysis of the rejection rate requirement analysis and the cost control requirement analysis of the thread machining.
7. And calculating to obtain the reliability of the chatter marks by adopting the established reliability prediction model of the chatter marks based on the response surface function, taking a comparison difference value with the target reliability as a target function, taking the processing technological parameters as design variables, performing reliability optimization iteration by using an improved non-dominated sorting genetic algorithm, finally meeting the requirement of the target reliability, and outputting a technological parameter optimization design result for controlling the degree of the chatter marks.
Further, according to the optimization design idea of the non-dominated sorting genetic algorithm, an optimization iterative process comprising genetic code generation, random initial population determination, fitness evaluation and offspring population calculation is implemented. Although the Pareto ranking values of all genetic individuals can be obtained and assessed through non-dominated ranking in the fitness assessment process so as to be close to the optimal solution, population density information around individuals of different levels cannot be assessed, and therefore the individuals with different optimization target approaches still have the same chance of breeding offspring, and optimization efficiency is reduced. The improvement is provided aiming at the defect of the original algorithm: on the basis of evaluating Pareto ranking values of individuals, sensitivity of optimization target approach to population density information around the individuals is evaluated by introducing individual variables and mean values and standard deviations of the ranking values of the individual variables, so that next generation inheritance of the individuals is far away from an area where the population is inactive, fitness evaluation rationality is increased, and optimization iteration efficiency is improved.
The process of the invention is described in detail below with reference to the examples:
in the embodiment shown in FIG. 1, a method for predicting and optimally controlling chatter defects in machining of an oil casing threaded joint is provided. A user establishes an original database of the actual condition of oil sleeve thread machining chatter marks, and inputs a plurality of groups of thread machining process parameters of different steel grades, specifications and thread types counted in the actual production process and corresponding actual chatter mark data of the thread surface into the original database. The processing technology parameter data comprises: the pipe body suspension length, the inner support and the floating support roller related to the rigidity of the pipe sample, the cutter bar diameter and the suspension length related to the rigidity of a cutter, the bearing clearance related to the rigidity of a lathe and bearing lubricating data; clamping pressure, jaw size and clamping contact area related to a pipe sample clamping mode; the clearance between the blade and the shim, the clamping tightness and the distance between the tool tip and the center of the lathe are related to the quality and the installation of the tool; depth of cut, feed, etc. associated with the machining process. Actual chatter data for a threaded surface, comprising: and (4) rating data for observing and detecting the severity of chatter marks on the surface of the actually machined thread.
Normalizing at least two groups of oil casing thread machining process parameter data with the same specification, steel grade and thread type and corresponding thread actual surface chatter data stored in an original database and abstracting the data into vectors, dividing the data after the normalization into training data samples and verification data samples, and respectively placing the training data samples and the verification data samples into a training sample library and a verification sample library;
performing data mining modeling on a training data sample by adopting the established improved K-means clustering algorithm, performing model correctness checking on a test data sample, and obtaining an oil casing thread machining chatter mark prediction model with machining process parameters as a dependent variable and thread surface chatter mark data as a variable based on a large database from practice;
predicting the generation degree of chatter marks under the specified process condition, and outputting a prediction result;
analyzing and acquiring a process parameter distribution model according to a large number of actually measured machine processing process parameters in a training sample library, and establishing a chatter texture reliability prediction model based on a response surface function through Monte Carlo simulation by combining the established chatter texture prediction expert model;
the target reliability of the design is determined through comprehensive analysis of thread machining rejection rate and cost control,
and calculating by adopting the established chatter mark reliability prediction model based on the response surface function to obtain chatter mark reliability, taking a comparison difference value with the target reliability as a target function, taking the processing process parameters as design variables, performing optimization iteration by using the established improved non-dominated sorting genetic algorithm, finally meeting the requirement of the target reliability, and outputting a process parameter optimization design result for controlling the chatter mark degree.
The above embodiments are only specific cases of the present invention, and the protection scope of the present invention includes but is not limited to the product form and style of the above embodiments, and any method for predicting and optimally controlling chatter defects in oil casing threaded joints according to the claims of the present invention and any suitable changes or modifications thereof by those skilled in the art shall fall within the protection scope of the present invention.
Claims (2)
1. A prediction and optimization control method for oil casing threaded joint machining chatter mark defects is characterized in that a plurality of groups of thread machining process parameters of different steel grades, specifications and thread types and corresponding actual chatter mark data of a thread surface are prestored in an original database; the processing technological parameter data comprises pipe body overhang length, an inner support and a floating support roller related to pipe sample rigidity, cutter bar diameter and overhang length related to cutter rigidity, bearing clearance and bearing lubricity data related to lathe rigidity, clamping pressure, jaw size and clamping contact area related to a pipe sample clamping mode, blade and tool pad clearance related to cutter quality and installation, clamping tightness and the distance between a cutter point and the center of a lathe; depth of cut, feed associated with the machining process; the actual chatter mark data of the thread surface comprises rating data for observing and detecting the severity of chatter marks on the actually machined thread surface; the method comprises the following steps:
s1, selecting at least two groups of oil casing thread machining process parameter data with the same specification, steel grade and thread type and corresponding thread actual surface chatter mark data stored in an original database, normalizing and abstracting the selected data into vectors, dividing the normalized and quantized data into training data samples and verification data samples, and respectively placing the training data samples and the verification data samples into a training sample library and a verification sample library;
s2, carrying out data mining modeling on the training data sample by adopting an improved K-means clustering algorithm to obtain a chatter mark production prediction model based on data mining for oil casing thread machining, wherein machining process parameters are used as dependent variables, and chatter mark data on the surface of threads are used as response variables; the K-means clustering algorithm is based on the principle that K points with the farthest batch distance are selected as initial clusters, firstly, one point is randomly selected as a first initial cluster center point, then, the point with the farthest batch distance is selected as a second initial cluster center point, then, the point with the largest closest distance between the first two points is selected as a third initial cluster center point, and the like until K objects are selected as initial cluster centers;
s3, verifying the correctness of the prediction model based on the data mining for the fibrillation production by using the check data sample, if the check is passed, obtaining a fibrillation prediction expert model, executing S4, otherwise, transposing S1, and selecting updated data to execute the process repeatedly;
s4, predicting the chatter mark generation degree under the specified process condition input by the user by adopting the obtained chatter mark prediction expert model, and outputting a chatter mark prediction result;
s5, analyzing and obtaining a process parameter distribution model according to a large number of actually measured machining process parameters in the training sample library, and establishing a reliability prediction model of the chatter marks based on the response surface function through Monte Carlo simulation by combining the chatter mark prediction expert model established in S4;
s6, comprehensively analyzing and determining the designed target reliability through the rejection rate requirement analysis and the cost control requirement analysis of the thread machining, checking the target reliability as a standard, taking the comparison difference between the chatter mark reliability and the target reliability in the chatter mark reliability prediction model obtained by calculation of S5 as a target function, taking the machining process parameters as design variables, performing reliability optimization iteration by using an improved non-dominated sorting genetic algorithm, finally meeting the requirement of the target reliability, and outputting a process parameter optimization design result for controlling chatter marks; the improved non-dominated sorting genetic algorithm is specifically implemented by an optimization iterative process comprising genetic code generation, random initial population determination, fitness evaluation and offspring population calculation, and on the basis of evaluating Pareto sorting values of individuals, sensitivity of optimization target nearness to population density information around the individuals is evaluated by introducing individual variables and mean values and standard differences of the sorting values of the individual variables, so that next generation inheritance of the individuals is far away from an inactive population region.
2. The method for predicting and optimally controlling the chatter mark defects in the machining of the oil casing threaded joint as recited in claim 1, wherein data mining modeling is performed in S2 according to the principle of the modified K-means clustering algorithm, and the data mining modeling step is:
(1) randomly selecting k objects from n process parameter mathematical vectors actually forming the chatter marks as initial cluster centers;
(2) calculating the distance between each object and the centers of the clusters according to the mean values of the objects in the clusters, and assigning each object to the most similar cluster;
(3) updating the cluster mean value, namely calculating the mean value of the objects in each cluster;
(4) looping (2) and (3) until each cluster criterion function no longer changes;
and completing the prediction of a plurality of process parameters generated by forming the chatter marks.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710780169.7A CN107391890B (en) | 2017-09-01 | 2017-09-01 | Prediction and optimal control method for oil casing threaded joint machining chatter defect |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710780169.7A CN107391890B (en) | 2017-09-01 | 2017-09-01 | Prediction and optimal control method for oil casing threaded joint machining chatter defect |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107391890A CN107391890A (en) | 2017-11-24 |
| CN107391890B true CN107391890B (en) | 2020-10-09 |
Family
ID=60348755
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710780169.7A Active CN107391890B (en) | 2017-09-01 | 2017-09-01 | Prediction and optimal control method for oil casing threaded joint machining chatter defect |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107391890B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110116254B (en) * | 2019-05-05 | 2021-07-02 | 中国石油天然气集团有限公司 | Method for predicting and controlling defects of annular welding joint of bimetal composite pipe for oil and gas gathering and transportation |
| CN112801137A (en) * | 2021-01-04 | 2021-05-14 | 中国石油天然气集团有限公司 | Petroleum pipe quality dynamic evaluation method and system based on big data |
| CN113408927B (en) * | 2021-06-30 | 2023-01-10 | 四川交达预应力工程检测科技有限公司 | Big data-based prestressed construction quality evaluation method and system |
| DE102021214320A1 (en) * | 2021-12-14 | 2023-06-15 | Sms Group Gmbh | System for machining workpieces and method for controlling a machine tool |
| CN116748352B (en) * | 2023-08-14 | 2023-11-07 | 江苏新恒基特种装备股份有限公司 | Metal pipe bending machine processing parameter monitoring control method, system and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003065179A3 (en) * | 2002-02-01 | 2003-11-06 | John Fairweather | A system and method for mining data |
| CN102609566A (en) * | 2012-01-12 | 2012-07-25 | 中国石油天然气集团公司 | Optimization design method for non-API (American petroleum institute) thread sealing face |
| CN105444923A (en) * | 2015-11-18 | 2016-03-30 | 浙江工业大学 | Mechanical temperature instrument error prediction method based on genetic-algorithm optimized least square support vector machine |
| CN106295795A (en) * | 2016-08-09 | 2017-01-04 | 衢州学院 | A kind of copper pipe interior whorl forming qualitative forecasting method based on BP neural network algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7613541B2 (en) * | 2003-03-28 | 2009-11-03 | Mitsubishi Denki Kabushiki Kaisha | Thread control method and system therefor |
-
2017
- 2017-09-01 CN CN201710780169.7A patent/CN107391890B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003065179A3 (en) * | 2002-02-01 | 2003-11-06 | John Fairweather | A system and method for mining data |
| CN102609566A (en) * | 2012-01-12 | 2012-07-25 | 中国石油天然气集团公司 | Optimization design method for non-API (American petroleum institute) thread sealing face |
| CN105444923A (en) * | 2015-11-18 | 2016-03-30 | 浙江工业大学 | Mechanical temperature instrument error prediction method based on genetic-algorithm optimized least square support vector machine |
| CN106295795A (en) * | 2016-08-09 | 2017-01-04 | 衢州学院 | A kind of copper pipe interior whorl forming qualitative forecasting method based on BP neural network algorithm |
Non-Patent Citations (5)
| Title |
|---|
| Chatter stability prediction in milling using time-varying uncertainties;Yu Liu 等;《The International Journal of Advanced Manufacturing Technology》;20170430;2627–2636 * |
| Prediction and experimental analysis of cutting forces during machining of precision external threads;Hamza K.Akyildiz 等;《Machining Science and Technology》;20110403;第15卷(第4期);485-506 * |
| 基于BP神经网络的大型螺纹旋风铣削表面粗糙度预测;周斌 等;《组合机床与自动化加工技术》;20150731(第7期);5-10 * |
| 梳刀加工接箍螺纹产生颤纹的原因及对策;杨建国;《煤矿机械》;20110228;第32卷(第02期);121-123 * |
| 铣削颤振及其可靠度分析;冯吉路 等;《组合机床与自动化加工技术》;20151231(第12期);8-11 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107391890A (en) | 2017-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107391890B (en) | Prediction and optimal control method for oil casing threaded joint machining chatter defect | |
| CN110116254B (en) | Method for predicting and controlling defects of annular welding joint of bimetal composite pipe for oil and gas gathering and transportation | |
| CN113176761B (en) | Quality prediction and technological parameter optimization method for multi-processing characteristic sheet part | |
| CN110722285B (en) | Laser hot wire welding seam forming quality prediction method, system and medium | |
| CN113469241B (en) | Product quality control method based on process network model and machine learning algorithm | |
| CN112610903A (en) | Water supply pipe network leakage positioning method based on deep neural network model | |
| CN109115383B (en) | Fatigue life prediction method for cold extrusion reinforced hole | |
| CN107627152B (en) | A kind of numerical control processing chip control method based on BP neural network | |
| CN111046341A (en) | Unconventional natural gas fracturing effect evaluation and capacity prediction method based on principal component analysis | |
| CN109522962B (en) | Chemical plant safety quantitative evaluation method | |
| CN101571717A (en) | Method and system for machining process control | |
| CN111077876B (en) | Power station equipment state intelligent evaluation and early warning method, device and system | |
| Kaya | RETRACTED: A genetic algorithm approach to determine the sample size for control charts with variables and attributes | |
| CN112149750A (en) | Water supply network pipe burst identification data driving method | |
| Hossain et al. | Surface roughness prediction model for ball end milling operation using artificial intelligence | |
| CN116018509A (en) | Method for producing steel pipe crushing strength prediction model, method for predicting crushing strength of steel pipe, method for determining manufacturing characteristics of steel pipe, and method for manufacturing steel pipe | |
| CN116737510A (en) | Data analysis-based intelligent keyboard monitoring method and system | |
| CN111882238A (en) | Gantry crane structure health assessment method based on cloud model and EAHP | |
| Vafadar et al. | Evaluation of the effect of product demand uncertainty on manufacturing system selection | |
| CN115755831A (en) | Fault diagnosis method and system based on fuzzy hierarchical analysis | |
| CN111062118B (en) | Multilayer soft measurement modeling system and method based on neural network prediction layering | |
| ZAKERI et al. | Tool wear modeling in drilling process of AISI1020 and AISI8620 using genetic programming | |
| CN117592223B (en) | Intelligent design method of hole machining tool for aerospace materials | |
| CN114925568B (en) | Fatigue life prediction and reliability analysis method for hinge beam structure of hexahedral top press | |
| CN113836488B (en) | Method and device for online data processing and state evaluation of steam turbine |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Jinxiang road 257000 in Shandong province Dongying city Dongying District No. 1 Applicant after: SHANDONG YONGLIJINGGONG PETROLEUM EQUIPMENT CO.,LTD. Address before: Jinxiang road 257000 in Shandong province Dongying city Dongying District No. 1 Applicant before: DONGYING CITY YONGLIJINGGONG PETROLEUM MACHINERY MANUFACTURING Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A prediction and optimal control method for machining chatter defect of oil casing threaded joint Effective date of registration: 20220316 Granted publication date: 20201009 Pledgee: Dongying Rural Commercial Bank Co.,Ltd. Pledgor: Shandong Yongli Jinggong Petroleum Equipment Co.,Ltd. Registration number: Y2022980002561 |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 257000 No.1, jinxiangshan Road, Dongying District, Dongying City, Shandong Province Patentee after: Shandong Yongli Jinggong Petroleum Equipment Co.,Ltd. Address before: 257000 No.1, jinxiangshan Road, Dongying District, Dongying City, Shandong Province Patentee before: SHANDONG YONGLIJINGGONG PETROLEUM EQUIPMENT CO.,LTD. |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20220928 Granted publication date: 20201009 Pledgee: Dongying Rural Commercial Bank Co.,Ltd. Pledgor: Shandong Yongli Jinggong Petroleum Equipment Co.,Ltd. Registration number: Y2022980002561 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Method for Predicting and Optimizing Control of Machining Chatter Flaws in Oil and Casing Threaded Joints Effective date of registration: 20221020 Granted publication date: 20201009 Pledgee: Weihai commercial bank Limited by Share Ltd. Dongying branch Pledgor: Shandong Yongli Jinggong Petroleum Equipment Co.,Ltd. Registration number: Y2022980019046 |