CN110842392A - Electric arc welding quality defect position prediction method - Google Patents

Electric arc welding quality defect position prediction method Download PDF

Info

Publication number
CN110842392A
CN110842392A CN201911175471.5A CN201911175471A CN110842392A CN 110842392 A CN110842392 A CN 110842392A CN 201911175471 A CN201911175471 A CN 201911175471A CN 110842392 A CN110842392 A CN 110842392A
Authority
CN
China
Prior art keywords
control
arc welding
welding
sample
quality
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.)
Pending
Application number
CN201911175471.5A
Other languages
Chinese (zh)
Inventor
王�锋
史亚斌
张磊
赵红武
秦海兵
张婷
尤煜
侯建华
贾恩宁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xi'an High Voltage Electrical Research Institute Co Ltd
Xian XD Transformer Co Ltd
Xian High Voltage Apparatus Research Institute Co Ltd
Original Assignee
Xi'an High Voltage Electrical Research Institute Co Ltd
Xian XD Transformer Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xi'an High Voltage Electrical Research Institute Co Ltd, Xian XD Transformer Co Ltd filed Critical Xi'an High Voltage Electrical Research Institute Co Ltd
Priority to CN201911175471.5A priority Critical patent/CN110842392A/en
Publication of CN110842392A publication Critical patent/CN110842392A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K31/00—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups
    • B23K31/12—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups relating to investigating the properties, e.g. the weldability, of materials
    • B23K31/125—Weld quality monitoring
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K9/00—Arc welding or cutting
    • B23K9/095—Monitoring or automatic control of welding parameters

Abstract

The invention discloses a method for predicting the position of an arc welding quality defect, which comprises the following steps: acquiring current, voltage and welding track of electric arc welding; according to current and voltage of arc welding, by T2Controlling the chart expression to obtain T2A control chart; joining the welding track of the arc welding with T2Controlling time axis synchronization of the graphs; and obtaining T through a control limit expression2Control limits on the control map; according to T2And controlling the time points corresponding to the parts exceeding the control limit on the control chart, and combining the welding machine track to obtain the positions of the arc welding quality defects. The invention converts two welding variables of current and voltage into T2The form of the control chart can greatly avoid the error judgment caused by the joint control of the unary control charts respectively; generating T by welding track and voltage current data2Controlling the time axis of the graph to be synchronized by T2Controlling the time of the abnormal position of the map according to the processing track and the time mapThe position where the quality defect possibly exists is pushed out, and convenience is brought to detection of welding quality.

Description

Electric arc welding quality defect position prediction method
Technical Field
The invention relates to the technical field of welding quality defect prediction, in particular to an arc welding quality defect position prediction method.
Background
As a traditional processing method, the electric arc welding has obviously improved welding performance along with the continuous development of a welding machine. However, the basic principle of arc welding using arc heat is not changed, and the quality of the arc has a direct relationship with the voltage and current. The prior art, although recording and analyzing current and voltage signals, does not disclose the analysis method. In the field of automation, there is also little concern with automated arc welding control methods for closed loop control methods that use quality as feedback because even if quality problems are detected during operation of automated arc welding, the reason for this cannot be determined due to the complexity of the process environment. Even if some defects are caused by abnormal current and voltage parameters, due to the particularity of the arc welding process and the fact that the overall quality of the welding is not influenced, the welding can only be repaired in a later period through later quality detection.
However, in some automatic arc welding fields, the work task of quality detection is very large due to the overlarge volume of a weldment, and a method capable of predicting the position of a welding defect undoubtedly brings convenience to detection of welding quality.
Disclosure of Invention
The embodiment of the invention provides a method for predicting the position of an arc welding quality defect, which is used for solving the problems in the prior art.
The embodiment of the invention provides a method for predicting the position of an arc welding quality defect, which comprises the following steps:
acquiring current, voltage and welding track of electric arc welding;
according to current and voltage of arc welding, by T2Controlling the chart expression to obtain T2A control chart;
joining the welding track of the arc welding with T2Controlling time axis synchronization of the graphs; and obtaining T through a control limit expression2Control limits on the control map;
according to T2Controlling the time point corresponding to the part exceeding the control limit on the graph, and combining with the welding machine track to obtain the position of the arc welding quality defect;
the T is2The control diagram expression is:
Figure BDA0002289831050000021
the control limit expression is as follows:
Figure BDA0002289831050000022
wherein K is a sample; n is the volume per sample;
Figure BDA0002289831050000023
is a sample mean vector;
Figure BDA0002289831050000024
is a sample nominal value vector, S is a covariance matrix of the quality characteristic values, p is the number of the quality characteristic values, m is the number of samples, F is normal distribution, and α is the probability of the first type of error.
Further, said T2Control chart expressionsThe forming specifically includes:
assuming that P quality characteristics obey P-element normal distribution, extracting m samples from the population, wherein the volume of each sample is n, and for a certain sample K, the sample mean values of different quality characteristic values form a sample mean value vector:
Figure BDA0002289831050000025
and (3) solving the total average value of each quality characteristic to form a sample nominal value vector:
Figure BDA0002289831050000026
statistic T of corresponding sample K2Comprises the following steps:
Figure BDA0002289831050000027
wherein [ S ]]p×pIs a covariance matrix of P quality property values:
Figure BDA0002289831050000031
the mean and variance, covariance for each sample are calculated as follows:
Figure BDA0002289831050000032
Figure BDA0002289831050000033
Figure BDA0002289831050000034
Sjhkrepresenting the covariance of the j-th and h-th quality characteristic values in the k-th sample; the average of the m samples for each statistic was found:
Figure BDA0002289831050000035
Figure BDA0002289831050000036
Figure BDA0002289831050000037
further, said T2The forming of the control chart specifically comprises the following steps:
p quality characteristic values are voltage U and current I and obey binary normal distribution; taking voltage U as X1The current I is taken as X2By substituting the current-voltage data, T is obtained2Control a chart.
Further, the number p of the quality characteristic values is 2.
The embodiment of the invention provides a method for predicting the position of an arc welding quality defect, which has the following beneficial effects compared with the prior art:
the invention converts the current and the voltage of two welding variables into T by carrying out statistical processing on the current and voltage data2The form of the control chart can greatly avoid the error judgment caused by the joint control of the unary control charts respectively. In addition, the invention is applied to the field of automatic welding, and the T generated by welding track and voltage current data2Controlling the time axis of the graph to be synchronized by T2And the time of the abnormal position of the control chart reversely deduces the position where the quality defect possibly exists according to the processing track and the time chart, thereby bringing convenience to welding quality detection.
Drawings
FIG. 1 is a flowchart of a method for predicting a defective location of arc welding according to an embodiment of the present invention;
FIG. 2 shows a diagram of T according to an embodiment of the present invention2Control a chart.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 to 2, an embodiment of the present invention provides a method for predicting a position of a quality defect of an arc welding, including:
step 1: and acquiring current, voltage and welding track of the arc welding.
Step 2: according to current and voltage of arc welding, by T2Controlling the chart expression to obtain T2Control a chart.
And step 3: joining the welding track of the arc welding with T2Controlling time axis synchronization of the graphs; and obtaining T through a control limit expression2Control limits on the map.
And 4, step 4: according to T2And controlling the time points corresponding to the parts exceeding the control limit on the control chart, and combining the welding machine track to obtain the positions of the arc welding quality defects.
The specific process of the steps 1-4 is as follows:
the welding quality and welding productivity are greatly affected by the magnitude of the welding current. The welding current mainly affects the size of the penetration. The current is too small, the electric arc is unstable, the fusion depth is small, the defects of incomplete penetration, slag inclusion and the like are easily caused, and the production rate is low; if the current is too large, the weld seam is prone to defects such as undercut and burn-through, and spatter is caused. Therefore, the welding current must be selected appropriately. In the welding process, the load of the welding machine is always changed due to the change of short circuit and arc length, and the output current and voltage of the welding machine are changed according to an external characteristic curve due to the existence of inductive reactance in a welding loop, so that the change range of the current and the voltage is large.
In the embodiment of the invention, assuming that P quality characteristics obey P-element normal distribution, m samples are extracted from the population, the capacity of each sample is n, and for a certain sample K, the sample mean values of different quality characteristic values form a sample mean value vector:
Figure BDA0002289831050000051
and (3) solving the total average value of each quality characteristic to form a sample nominal value vector:
Figure BDA0002289831050000052
statistic T of corresponding sample K2Comprises the following steps:
Figure BDA0002289831050000053
wherein [ S ]]p×pIs a covariance matrix of P quality property values:
Figure BDA0002289831050000054
the mean and variance, covariance for each sample are calculated as follows:
Figure BDA0002289831050000055
Figure BDA0002289831050000056
Sjhkrepresenting the covariance of the j-th and h-th quality characteristic values in the k-th sample; the average of the m samples for each statistic was found:
Figure BDA0002289831050000058
Figure BDA0002289831050000059
the P quality characteristic values are voltage U and current I and obey binary normal distribution; taking voltage U as X1The current I is taken as X2By substituting the current-voltage data, T is obtained2Control a chart.
Finally, the control limit expression is:
Figure BDA0002289831050000061
wherein K is a sample; n is the volume per sample;
Figure BDA0002289831050000062
is a sample mean vector;
Figure BDA0002289831050000063
is a sample nominal value vector, S is a covariance matrix of the quality characteristic values, p is the number of the quality characteristic values, m is the number of samples, F is a normal distribution, α is the probability of a first type of error, the number p of the quality characteristic values takes the value of 2, Fs,m-sAnd (α) checking the numerical value to obtain a table, wherein after the welding operation is finished, α can be selected to obtain a control limit, the part exceeding the control limit is a time point at which a quality defect possibly exists, and the welding track data is searched according to the time point to obtain a welding position for subsequent quality defect inspection and repair of the defect.
It should be noted that, in the embodiment of the present invention, a multivariable control diagram is adopted, and the multivariable control diagram is composed of a voltage I and a current U.
Example (b):
the invention is further explained by combining the attached drawings, and 40mm plates are taken and subjected to a flat welding experiment respectively and combined with a control chart to predict defects. The welding was performed at a voltage of 25V and a current of 180A, and the data shown in Table 1 was substituted into the following equation to obtain a control chart shown in FIG. 2.
Figure BDA0002289831050000064
TABLE 1
Figure BDA0002289831050000065
Table 1 shows the data required for the control chart obtained by calculating the current and voltage data collected by performing the flat welding experiment on each 40mm plate and predicting the defect by combining the control chart.
Referring to the flow shown in fig. 1, selecting a reasonable probability α of the first type of error, and further obtaining a control limit, as shown in fig. 2, the part higher than the control limit is a time node where the quality defect may exist, and searching the welding track data according to the corresponding time node to obtain a corresponding position.
The above disclosure is only a few specific embodiments of the present invention, and those skilled in the art can make various modifications and variations of the present invention without departing from the spirit and scope of the present invention, and it is intended that the present invention encompass these modifications and variations as well as others within the scope of the appended claims and their equivalents.

Claims (4)

1. An arc welding quality defect position prediction method is characterized by comprising the following steps:
acquiring current, voltage and welding track of electric arc welding;
according to current and voltage of arc welding, by T2Controlling the chart expression to obtain T2A control chart;
joining the welding track of the arc welding with T2Controlling time axis synchronization of the graphs; and obtaining T through a control limit expression2Control limits on the control map;
according to T2Controlling the time point corresponding to the part exceeding the control limit on the graph, and combining with the welding machine track to obtain the position of the arc welding quality defect;
the T is2The control diagram expression is:
Figure FDA0002289831040000011
the control limit expression is as follows:
Figure FDA0002289831040000012
wherein K is a sample; n is the volume per sample;
Figure FDA0002289831040000013
is a sample mean vector;
Figure FDA0002289831040000014
is a sample nominal value vector, S is a covariance matrix of the quality characteristic values, p is the number of the quality characteristic values, m is the number of samples, F is normal distribution, and α is the probability of the first type of error.
2. The arc welding quality defect location prediction method of claim 1, wherein T is2Controlling the formation of the expression, specifically comprising:
assuming that P quality characteristics obey P-element normal distribution, extracting m samples from the population, wherein the volume of each sample is n, and for a certain sample K, the sample mean values of different quality characteristic values form a sample mean value vector:
Figure FDA0002289831040000015
and (3) solving the total average value of each quality characteristic to form a sample nominal value vector:
statistic T of corresponding sample K2Comprises the following steps:
Figure FDA0002289831040000021
wherein [ S ]]p×pIs a covariance matrix of P quality property values:
Figure FDA0002289831040000022
the mean and variance, covariance for each sample are calculated as follows:
Figure FDA0002289831040000023
Figure FDA0002289831040000024
Figure FDA0002289831040000025
Sjhkrepresenting the covariance of the j-th and h-th quality characteristic values in the k-th sample; the average of the m samples for each statistic was found:
Figure FDA0002289831040000026
Figure FDA0002289831040000027
3. the arc welding quality defect location prediction method of claim 2, wherein T is2The forming of the control chart specifically comprises the following steps:
p quality characteristic values are voltage U and current I and obey binary normal distribution; taking voltage U as X1The current I is taken as X2By substituting the current-voltage data, T is obtained2Control a chart.
4. The arc welding quality defect position prediction method according to claim 1, wherein the number p of the quality characteristic values takes a value of 2.
CN201911175471.5A 2019-11-26 2019-11-26 Electric arc welding quality defect position prediction method Pending CN110842392A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911175471.5A CN110842392A (en) 2019-11-26 2019-11-26 Electric arc welding quality defect position prediction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911175471.5A CN110842392A (en) 2019-11-26 2019-11-26 Electric arc welding quality defect position prediction method

Publications (1)

Publication Number Publication Date
CN110842392A true CN110842392A (en) 2020-02-28

Family

ID=69604737

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911175471.5A Pending CN110842392A (en) 2019-11-26 2019-11-26 Electric arc welding quality defect position prediction method

Country Status (1)

Country Link
CN (1) CN110842392A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1266391A (en) * 1997-08-08 2000-09-13 株式会社安川电机 Arc welding monitoring device
US6583386B1 (en) * 2000-12-14 2003-06-24 Impact Engineering, Inc. Method and system for weld monitoring and tracking
EP2474380A1 (en) * 2009-07-02 2012-07-11 Soudronic AG Method and welding device for analysing the welding electric current for container clamp welding
CN104379291A (en) * 2012-04-23 2015-02-25 林肯环球股份有限公司 System and method for monitoring weld quality
CN107004375A (en) * 2014-06-27 2017-08-01 伊利诺斯工具制品有限公司 The system and method for monitoring weld information

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1266391A (en) * 1997-08-08 2000-09-13 株式会社安川电机 Arc welding monitoring device
US6583386B1 (en) * 2000-12-14 2003-06-24 Impact Engineering, Inc. Method and system for weld monitoring and tracking
EP2474380A1 (en) * 2009-07-02 2012-07-11 Soudronic AG Method and welding device for analysing the welding electric current for container clamp welding
CN104379291A (en) * 2012-04-23 2015-02-25 林肯环球股份有限公司 System and method for monitoring weld quality
CN107004375A (en) * 2014-06-27 2017-08-01 伊利诺斯工具制品有限公司 The system and method for monitoring weld information

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
徐鹏航: "《质量管理指南》", 28 February 1995, 中国时政经济出版社 *
曾安等: "基于MSPC方法的GMAW在线监控", 《焊接学报》 *

Similar Documents

Publication Publication Date Title
CN111047225B (en) SMT surface mounting component welding spot quality evaluation method based on edge side model processing
CN108960306B (en) Solder paste detection threshold value optimization method based on SMT big data
CN112329860B (en) Mixed deep learning visual detection method, device, equipment and storage medium
CN116560327B (en) Electric tool production control method and system based on Internet of things
CN113762410B (en) Key welding process parameter prediction method based on machine learning
CN111815555A (en) Metal additive manufacturing image detection method and device combining anti-neural network with local binary
CN111015006B (en) Online monitoring method for laser-arc hybrid welding quality based on spectral information
CN112487708A (en) Resistance spot welding quality prediction method based on ensemble learning
CN112091472A (en) Welding process quality fusion judgment method and device
CN111872589B (en) Welding test control method, system, computer storage medium and equipment
CN112580935A (en) Industrial product production process traceability analysis method based on machine vision
CN111178156B (en) Time sequence feature effective window extraction method applied to machine learning
CN115609112A (en) Welding parameter determination method, device and medium thereof
CN113505657B (en) Welding spot quality detection method and device
Gröning et al. Method of process optimization for LMD-processes using machine learning algorithms
CN114646665A (en) Arc welding defect real-time detection method and system
CN114330491A (en) Method for optimizing quality of welding spot through analysis guidance of resistance spot welding curve
KR102353574B1 (en) Tool-related abnormal data detection system of CNC machines
CN110842392A (en) Electric arc welding quality defect position prediction method
CN116451045B (en) Welding process steady-state current calculation method
CN108242411B (en) Method and system for managing defects on a line
Liyakat et al. ML in the Electronics Manufacturing Industry
CN116777391A (en) Welding process management system and welding process rule generation method and system
CN114818997B (en) Burn-through fault prediction method based on high-frequency welding time sequence data
CN115446504A (en) Welding method and welding system

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20200228