CN113076350A - Welding abnormity detection method and device, computer equipment and storage medium - Google Patents
Welding abnormity detection method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113076350A CN113076350A CN202110228624.9A CN202110228624A CN113076350A CN 113076350 A CN113076350 A CN 113076350A CN 202110228624 A CN202110228624 A CN 202110228624A CN 113076350 A CN113076350 A CN 113076350A
- Authority
- CN
- China
- Prior art keywords
- welding
- detection
- model
- abnormity detection
- models
- 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
- 238000003466 welding Methods 0.000 title claims abstract description 561
- 238000001514 detection method Methods 0.000 title claims abstract description 485
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 50
- 230000004044 response Effects 0.000 claims abstract description 20
- 230000002159 abnormal effect Effects 0.000 claims description 77
- 238000012360 testing method Methods 0.000 claims description 63
- 230000005856 abnormality Effects 0.000 claims description 47
- 230000008569 process Effects 0.000 claims description 33
- 230000004927 fusion Effects 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 23
- 238000002372 labelling Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000013499 data model Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- HSFWRNGVRCDJHI-UHFFFAOYSA-N Acetylene Chemical compound C#C HSFWRNGVRCDJHI-UHFFFAOYSA-N 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000013215 result calculation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/211—Schema design and management
- G06F16/212—Schema design and management with details for data modelling support
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Probability & Statistics with Applications (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Software Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application relates to a welding abnormity detection method, a welding abnormity detection device, computer equipment and a storage medium. The method comprises the steps of receiving a welding abnormity detection request; feeding back various preset welding abnormity detection models; acquiring corresponding model combination information and weight setting information; inputting welding data into a preset welding abnormity detection model, and acquiring detection results of each model corresponding to the welding data; and receiving a multi-model welding abnormity detection result corresponding to the welding abnormity detection request according to each model detection result and the weight setting information. According to the method and the device, after the welding abnormity detection request is received, the response site detection personnel select the proper operation of the preset welding abnormity detection model combination according to various preset welding abnormity detection models which are fed back, and the weight proportion of the models is set by the response site detection personnel, so that the welding abnormity detection recognition rate aiming at various welding data is improved under the conditions of different requirements on the basis of complicated and changeable working conditions.
Description
Technical Field
The present application relates to the field of welding technologies, and in particular, to a welding anomaly detection method and apparatus, a computer device, and a storage medium.
Background
Welding is one of the most important processes in the field of mechanical manufacturing, and can be divided into manual welding, semi-automatic welding, automatic welding and the like according to different welding properties, modes, application occasions and the like. Due to the occurrence of welding abnormity in the welding process, phenomena of welding missing, welding penetration, uneven welding line forming and the like of a welded product are often caused. Therefore, it is necessary to perform welding abnormality detection after welding is completed, thereby ensuring the quality of the welded product.
Welding abnormity detection can be generally carried out through an abnormity detection model at present, however, during welding detection, the requirements of a customer on a welding product and the welding working conditions are changed along with the requirements of orders, and at this time, all conditions of welding abnormity cannot be met through a single abnormity detection model, so that the identification rate of welding abnormity detection is influenced.
Disclosure of Invention
In view of the above, it is necessary to provide a welding abnormality detection method, a welding abnormality detection apparatus, a computer device, and a storage medium, which can improve a welding abnormality detection recognition rate in response to different needs.
A welding anomaly detection method, the method comprising:
receiving a welding abnormity detection request, and determining welding data corresponding to the welding abnormity detection request;
feeding back various preset welding abnormity detection models according to the welding abnormity detection request;
acquiring model combination information and weight setting information corresponding to the various preset welding abnormity detection models, wherein the model combination information is corresponding selection information of the preset welding abnormity detection model used in the welding abnormity detection process;
searching preset welding abnormity detection models specified by the model combination information from the various preset welding abnormity detection models, inputting the welding data into the preset welding abnormity detection models corresponding to the model combination information, and acquiring each model detection result corresponding to the welding data;
and acquiring a multi-model welding abnormity detection result corresponding to the welding abnormity detection request according to each model detection result and the weight setting information.
In one embodiment, the obtaining of the model combination information and the weight setting information corresponding to the various preset welding anomaly detection models includes:
acquiring model combination information corresponding to the various preset welding abnormity detection models;
searching historical weight setting information ranking of the model combination corresponding to the model combination information in historical data;
setting a recommendation table according to the historical weight setting information ranking feedback weight;
and acquiring weight setting information fed back according to the weight setting recommendation table.
In one embodiment, the obtaining of the model combination information and the weight setting information corresponding to the various preset welding anomaly detection models includes:
obtaining model combination information corresponding to the various preset welding abnormity detection models, and feeding back corresponding test welding data with result labels according to the model combination information;
acquiring test weight setting data corresponding to the test welding data;
acquiring the test welding data and a multi-model welding abnormity test result corresponding to the test weight setting data through a preset welding abnormity detection model corresponding to the model combination information;
feeding back the multi-mode welding abnormity test result;
and acquiring weight setting information fed back according to the multimode welding abnormity test result.
In one embodiment, the feeding back various types of preset welding abnormality detection models according to the welding abnormality detection request includes:
acquiring historical response time and historical recognition rate corresponding to various preset welding anomaly detection models;
performing information labeling on the various preset welding abnormity detection models according to the historical response time and the historical recognition rate;
and various preset welding abnormity detection models are marked according to the welding abnormity detection request feedback information.
In one embodiment, the obtaining, according to the detection results of the models and the weight setting information, the multiple-model welding abnormality detection result corresponding to the welding abnormality detection request includes:
acquiring an abnormal detection weighted fusion result according to the detection results of the models and the weight setting information;
and when the weighted fusion result of the abnormal detection is larger than or equal to a preset abnormal detection threshold value, judging that the multi-model welding abnormal detection result corresponding to the welding abnormal detection request is normal welding, and when the weighted fusion result of the abnormal detection is smaller than the preset abnormal detection threshold value, judging that the multi-model welding abnormal detection result corresponding to the welding abnormal detection request is abnormal welding.
In one embodiment, after obtaining the multi-mode welding anomaly detection result corresponding to the welding anomaly detection request according to the detection results of the models and the weight setting information, the method further includes:
when the multi-mode welding abnormity detection result is abnormal welding, generating a welding detection report of the multi-mode welding abnormity detection result;
and feeding back the welding detection report.
A welding anomaly detection device, said device comprising:
the request acquisition module is used for receiving a welding abnormity detection request and determining welding data corresponding to the welding abnormity detection request;
the model feedback module is used for feeding back various preset welding abnormity detection models according to the welding abnormity detection request;
the information setting module is used for acquiring model combination information and weight setting information corresponding to various preset welding abnormity detection models, wherein the model combination information is corresponding selection information of the preset welding abnormity detection models used in the welding abnormity detection process;
the model detection module is used for searching preset welding abnormity detection models specified by the model combination information from the various preset welding abnormity detection models, inputting the welding data into the preset welding abnormity detection models corresponding to the model combination information, and acquiring each model detection result corresponding to the welding data;
and the abnormality detection module is used for acquiring a multi-model welding abnormality detection result corresponding to the welding abnormality detection request according to the detection results of the models and the weight setting information.
In one embodiment, the information setting module is specifically configured to:
acquiring model combination information corresponding to the various preset welding abnormity detection models;
searching historical weight setting information ranking of the model combination corresponding to the model combination information in historical data;
setting a recommendation table according to the historical weight setting information ranking feedback weight;
and acquiring weight setting information fed back according to the weight setting recommendation table.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
receiving a welding abnormity detection request, and determining welding data corresponding to the welding abnormity detection request;
feeding back various preset welding abnormity detection models according to the welding abnormity detection request;
acquiring model combination information and weight setting information corresponding to the various preset welding abnormity detection models, wherein the model combination information is corresponding selection information of the preset welding abnormity detection model used in the welding abnormity detection process;
searching preset welding abnormity detection models specified by the model combination information from the various preset welding abnormity detection models, inputting the welding data into the preset welding abnormity detection models corresponding to the model combination information, and acquiring each model detection result corresponding to the welding data;
and acquiring a multi-model welding abnormity detection result corresponding to the welding abnormity detection request according to each model detection result and the weight setting information.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
receiving a welding abnormity detection request, and determining welding data corresponding to the welding abnormity detection request;
feeding back various preset welding abnormity detection models according to the welding abnormity detection request;
acquiring model combination information and weight setting information corresponding to the various preset welding abnormity detection models, wherein the model combination information is corresponding selection information of the preset welding abnormity detection model used in the welding abnormity detection process;
searching preset welding abnormity detection models specified by the model combination information from the various preset welding abnormity detection models, inputting the welding data into the preset welding abnormity detection models corresponding to the model combination information, and acquiring each model detection result corresponding to the welding data;
and acquiring a multi-model welding abnormity detection result corresponding to the welding abnormity detection request according to each model detection result and the weight setting information.
According to the welding abnormity detection method, the welding abnormity detection device, the computer equipment and the storage medium, the welding data corresponding to the welding abnormity detection request is determined by receiving the welding abnormity detection request; feeding back various preset welding abnormity detection models according to the welding abnormity detection request; acquiring model combination information and weight setting information corresponding to various preset welding abnormity detection models; searching preset welding abnormity detection models specified by model combination information from various preset welding abnormity detection models, inputting welding data into the preset welding abnormity detection models corresponding to the model combination information, and acquiring detection results of the models corresponding to the welding data; and receiving a multi-model welding abnormity detection result corresponding to the welding abnormity detection request according to each model detection result and the weight setting information. According to the welding anomaly detection method and device, after the welding anomaly detection request is received, various preset welding anomaly detection models are fed back, then the anomaly detection of the welding process is carried out according to model combination information and weight setting information fed back by field detection personnel, namely, the welding anomaly detection is carried out through the flexible matching of the detection models and the weights provided by the field detection personnel, and therefore the welding anomaly detection recognition rate aiming at various welding data can be improved under the conditions of different requirements of complicated and changeable working conditions.
Drawings
FIG. 1 is a diagram of an exemplary welding anomaly detection method;
FIG. 2 is a schematic flow chart of a weld anomaly detection method in one embodiment;
FIG. 3 is a performance diagram of various weld anomaly detection models in one embodiment;
FIG. 4 is a performance diagram of various weld anomaly detection models in one embodiment;
FIG. 5 is a schematic sub-flow chart of step 205 of FIG. 2 in one embodiment;
FIG. 6 is a schematic sub-flow chart of step 205 of FIG. 2 according to another embodiment;
FIG. 7 is a schematic sub-flow chart of step 203 of FIG. 2 in one embodiment;
FIG. 8 is a block diagram showing the structure of a welding abnormality detection apparatus according to an embodiment;
FIG. 9 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The welding abnormity detection method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. When a welding detection worker at the terminal 102 needs to detect a welding result, it is determined whether welding is abnormal. The welding data corresponding to the welding anomaly detection request may be submitted simultaneously by sending the corresponding welding anomaly detection request to the server 104. The welding data is detected by the server 104 to determine whether there is welding anomaly in the welding process. The server 104 receives the welding abnormity detection request and determines welding data corresponding to the welding abnormity detection request; feeding back various preset welding abnormity detection models according to the welding abnormity detection request; acquiring model combination information and weight setting information corresponding to various preset welding abnormity detection models; searching preset welding abnormity detection models specified by model combination information from various preset welding abnormity detection models, inputting welding data into the preset welding abnormity detection models corresponding to the model combination information, and acquiring detection results of the models corresponding to the welding data; and receiving a multi-model welding abnormity detection result corresponding to the welding abnormity detection request according to each model detection result and the weight setting information. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a welding anomaly detection method is provided, which is described by taking the method as an example applied to the server 104 in fig. 1, and includes the following steps:
step 201, receiving a welding abnormity detection request, and determining welding data corresponding to the welding abnormity detection request.
The welding abnormality detection request is used for requesting the server 104 to perform abnormality detection on the specified welding data to determine whether an abnormality exists in the welding process corresponding to the welding data. The welding data specifically refers to various data generated in the welding process, including data such as welding variables, welding curves, and welding information in the welding process. For ultrasonic welding, the welding data may specifically include welding current, machine Ready signal, welding voltage, welding ultrasonic output control signal, cylinder lift and drop control signal, welding gas pressure, probe position detected by a sensor, voltage phase difference, current phase difference, phase discrimination result, welding frequency, active power, reactive power, and other welding related data of the welding process.
Specifically, after welding is completed, if a welding detection worker at the terminal 102 needs to verify a welding process and it is ensured that no abnormality occurs in a welding result, a welding abnormality detection request may be sent to the server 104 to request the server 104 to perform corresponding welding abnormality detection. In one embodiment, the welding anomaly detection request may be automatically sent to the server 104 after the welding is completed, without manual sending by a worker, and by automatically sending the welding anomaly detection request, the detection efficiency may be effectively improved. The server 104 further determines the welding data corresponding to the welding anomaly detection request after receiving the welding anomaly detection request. In one embodiment, the weld anomaly detection request may include corresponding weld data. In another embodiment, the welding anomaly detection request may include information such as a data flag or a storage address of the corresponding welding data, and the server 104 may determine the welding data corresponding to the welding anomaly detection request according to the data flag or the storage address after the welding anomaly detection request.
And 203, feeding back various preset welding abnormity detection models according to the welding abnormity detection request.
The various preset welding abnormity detection models are models for detecting welding abnormity, and can be divided into a mechanism model and a data model in principle, and can be divided into four types according to modeling complexity. The various welding anomaly detection models have advantages and disadvantages in response speed, accuracy, interpretability and maintenance difficulty, and reference can be made to fig. 3. In an actual field, after a welding expert defines some high-recognition-rate data models or mechanism models for deployment, the requirements of customers and welding conditions are changed along with the requirements of orders, and at this time, a single-type anomaly detection model generally cannot meet all conditions, so that a multi-model fusion system is considered for welding anomaly detection. In the application, the types specifically included in each preset welding anomaly detection model include a welding curve similarity judgment model, a welding variable expert system judgment model, a welding curve depth learning judgment model, a welding energy anomaly judgment model and the like. Meanwhile, each type of model has different parameter configurations in a model base of the server, and the module maintains default parameters of all models, such as the threshold value of a welding energy abnormity judgment model, the network structure in a welding curve deep learning judgment model, the number of layers, the iteration times and other parameters.
Specifically, a plurality of preset welding anomaly detection models are prestored in the server, each model is stored locally in a file (for example, a pkl format file) form, and after a welding anomaly detection request is received, the server feeds back various preset welding anomaly detection models to a welding detection worker according to a request of the terminal 102 so as to perform multi-model fusion welding anomaly detection setting.
In step 205, model combination information and weight setting information corresponding to various preset welding anomaly detection models are obtained, wherein the model combination information is corresponding selection information of the preset welding anomaly detection models used in the welding anomaly detection process.
The model combination information refers to information that is fed back to the server 104 after a welding detection worker selects various preset welding abnormality detection models fed back, and determines which models the welding data corresponding to the welding abnormality detection request needs to pass through for abnormality detection. The weight setting information refers to data corresponding to the weight proportion of each model in the model combination information in the last welding abnormity detection process, and different models contribute different to the final detection result, so that the abnormity detection identification rate can be improved through weight setting.
Specifically, the server 104 may feed back various preset welding anomaly detection models specifically in a form of a list, and a welding detection worker may perform selection in the list to perform model selection in the welding anomaly detection process. And meanwhile, filling the weight proportion corresponding to the model to feed back corresponding weight setting information. According to the model information and the customer requirements, welding detection workers can perform corresponding model selection and weight setting to ensure the identification rate of welding abnormity detection.
Step 207, searching preset welding abnormity detection models designated by the model combination information from various preset welding abnormity detection models, inputting welding data into the preset welding abnormity detection models corresponding to the model combination information, and obtaining detection results of each model corresponding to the welding data.
And 209, receiving a multi-model welding abnormity detection result corresponding to the welding abnormity detection request according to each model detection result and the weight setting information.
Each model detection result is data obtained after welding data is calculated by each preset welding abnormity detection model corresponding to the model combination information, and the data comprises a plurality of same or different abnormity detection results. And the multi-mode welding abnormity detection result corresponding to the welding abnormity detection request is a final detection result obtained by performing multi-model fusion calculation according to each model detection result and the weight setting information.
Specifically, when the weight of each model is configured, welding data can be input into each model for calculation, in the process, each model performs anomaly detection on the welding data, a final model detection result is output to the server 104, the server 104 performs weighted fusion on the model monitoring results of each model and outputs the model monitoring results, and the obtained result is a final multimode welding anomaly detection result. In one embodiment, each preset welding abnormality detection model only outputs two results, namely "OK (welding absence abnormality)" and "NG (welding presence abnormality)", so that the weighted output logic only needs to judge which result weight is above 0.5 to be considered as the final output. As shown in fig. 4, the abnormality recognition result of the models 1 and 3 for the input welding data is OK, the recognition result of the model 2 is NG, the occupancy of OK is 0.7 and the occupancy of NG is 0.3 in combination with the weight, so that the final output after the weighted fusion is OK, that is, the multimode welding abnormality detection result corresponding to the welding data is that there is no abnormality.
According to the welding abnormity detection method, welding data corresponding to the welding abnormity detection request is determined by receiving the welding abnormity detection request; feeding back various preset welding abnormity detection models according to the welding abnormity detection request; acquiring model combination information and weight setting information corresponding to various preset welding abnormity detection models; searching preset welding abnormity detection models specified by model combination information from various preset welding abnormity detection models, inputting welding data into the preset welding abnormity detection models corresponding to the model combination information, and acquiring detection results of the models corresponding to the welding data; and receiving a multi-model welding abnormity detection result corresponding to the welding abnormity detection request according to each model detection result and the weight setting information. According to the welding anomaly detection method and device, after the welding anomaly detection request is received, various preset welding anomaly detection models are fed back, then the anomaly detection of the welding process is carried out according to model combination information and weight setting information fed back by field detection personnel, namely the detection models and the flexible proportion of the weights are provided by the field detection personnel, and therefore the welding anomaly detection recognition rate aiming at various welding data can be improved under the conditions of different requirements of complicated and changeable working conditions.
In one embodiment, as shown in FIG. 5, step 205 comprises:
step 502, model combination information corresponding to various preset welding abnormity detection models is obtained.
Step 504, searching historical weight setting information ranking of the model combination corresponding to the model combination information in historical data.
Step 506, ranking the feedback weight setting recommendation table according to the historical weight setting information.
And step 508, acquiring the weight setting information fed back according to the weight setting recommendation table.
The historical weight setting information is weight size configuration information corresponding to each preset welding abnormality detection model in historical welding abnormality detection aiming at the model combination of the current model combination information. The historical weight setting information ranking is information obtained by ranking the weight setting in the historical data according to the set times.
Specifically, the welding inspection worker at the terminal 102 may first select which models need to be used and submit the corresponding model combination information to the server. Then, the server 104 extracts and summarizes the weight setting schemes corresponding to the model combinations in the historical data based on the historical data and the models selected by the current welding detection workers, and determines the historical weight setting information ranking according to the frequency of the welding detection workers. Setting a recommendation table to welding detection workers according to the historical weight setting information ranking feedback weight, and selecting corresponding weight setting by the welding detection workers according to the recommendation table; the server 104 acquires the weight setting information fed back by the welding detection staff according to the weight setting recommendation table. In this embodiment, the server 104 may recommend the most multi-model weight setting coefficients to be selected by the welding detection staff according to the model selected by the welding detection staff, thereby saving the trial and error time of the welding detection staff and improving the work efficiency.
In one embodiment, as shown in FIG. 6, step 205 comprises:
step 601, obtaining model combination information corresponding to various preset welding abnormity detection models, and feeding back corresponding test welding data with result labels according to the model combination information.
Step 603, test weight setting data corresponding to the test welding data is obtained.
And 605, acquiring test welding data and a multi-model welding abnormity test result corresponding to the test weight setting data through a preset welding abnormity detection model corresponding to the model combination information.
And step 607, feeding back the multi-mode welding abnormity test result.
And step 609, acquiring weight setting information fed back according to the multi-model welding abnormity test result.
The test welding data with the result labels are used for providing model debugging for the model corresponding to the model combination information of the current welding detection workers, and therefore the optimal weight setting is determined. The test weight setting data and the multimode welding abnormity test result are respectively intermediate data in the model debugging process and correspond to the weight setting information and the multimode welding abnormity detection result.
Specifically, after the welding detection worker feeds back the model combination information through the terminal 102, it may also be determined whether to debug the selected model combination, after the model debugging is determined, the server 104 may feed back the corresponding test welding data with the result label according to the model combination information, the welding detection worker may select the test welding data to use, and then perform weight setting on the test welding data, and feed back the corresponding test weight setting data to the server 104. Referring to the above test process, the server 104 may obtain the test welding data and the multi-model welding anomaly test result corresponding to the test weight setting data through the preset welding anomaly detection model corresponding to the model combination information. The above steps 603 to 607 may be performed repeatedly, then the welding detection worker may select different weights to test the welding data for one time to perform model debugging, and then determine the selected weight according to the test welding data and the multi-model welding anomaly test result in the iterative calculation process, and finally the server 104 obtains weight setting information fed back by the welding detection worker according to the multi-model welding anomaly test result. In this embodiment, the model result may be manually verified and the weight may be manually changed through the model debugging process, and all records of the model debugging may be saved and used as sample data for subsequent optimization.
In one embodiment, as shown in fig. 7, step 203 comprises:
step 702, obtaining historical response time and historical recognition rate corresponding to various preset welding abnormity detection models.
And step 704, performing information labeling on various preset welding abnormity detection models according to the historical response time and the historical recognition rate.
And step 706, feeding back various preset welding abnormity detection models marked by the information according to the welding abnormity detection request.
And obtaining historical data in the model operation process based on the historical response time and the historical recognition rate. Specifically, when the model information is fed back to the welding detection worker at the terminal 102 side, some algorithm models can be selected from a built-in model library of the server, and after selection, the interface displays the historical response time and the historical recognition rate of each model in the past welding abnormality detection. And then, the welding detection staff on the side of the terminal 102 selects the required model based on the historical response time, the historical recognition rate and other auxiliary information according to the model information and the customer requirements, and then performs the subsequent weight setting step. In this embodiment, information labeling is performed on various preset welding anomaly detection models, so that welding detection workers at the terminal 102 side can be helped to know the model operation condition, and therefore the processing efficiency of the model selection process and the accuracy of model selection are improved.
In one embodiment, step 209 comprises: acquiring an abnormal detection weighted fusion result according to each model detection result and the weight setting information; and when the weighted fusion result of the abnormal detection is larger than or equal to the preset abnormal detection threshold value, judging that the multi-model welding abnormal detection result corresponding to the welding abnormal detection request is normal welding, and when the weighted fusion result of the abnormal detection is smaller than the preset abnormal detection threshold value, judging that the multi-model welding abnormal detection result corresponding to the welding abnormal detection request is abnormal welding.
Specifically, when performing weighted fusion, an anomaly detection weighted fusion result may be obtained according to each model detection result and the weight setting information. In one embodiment, each preset welding abnormality detection model only outputs two results, namely "OK (welding absence abnormality)" and "NG (welding presence abnormality)", so that the weighted output logic only needs to judge which result weight is above 0.5 to be considered as the final output. In another embodiment, each preset welding anomaly detection model outputs an anomaly score corresponding to the welding data, and the calculation process of the final anomaly detection weighted fusion result of the welding data includes: and performing product operation on the abnormal scores of the welding data and the corresponding weights by the models to obtain the weighted scores corresponding to the models, and then adding all the weighted scores to obtain the final fusion abnormal score. And judging whether the multi-model welding abnormity detection result corresponding to the welding abnormity detection request is welding abnormity or normal through whether the fusion abnormity score is larger than or equal to a preset abnormity detection threshold value. In this embodiment, the model detection result and the weight setting information are subjected to weighted calculation, and then the weighted calculation result is compared with the preset abnormal detection threshold value to obtain a final welding detection result, so that the final welding detection result can be effectively calculated, and the accuracy of welding result calculation is ensured.
In one embodiment, after step 209, the method further includes: when the multi-mode welding abnormity detection result is abnormal welding, generating a welding detection report of the multi-mode welding abnormity detection result; and feeding back a welding detection report.
Specifically, when it is determined that the multi-model welding abnormality detection result corresponding to the welding abnormality detection request is abnormal welding, the corresponding abnormality alarm is triggered, and an alarm signal is transmitted to the response interface of the server. Meanwhile, when an abnormal alarm is triggered, the server 104 automatically generates a welding detection report corresponding to the multi-model welding abnormal detection result, so that fault recording and tracing are facilitated, and the welding detection report includes, but is not limited to, welding time, cell codes, tab codes, configuration information of each model, judgment results of each model, output information of each model (data models output similarity, abnormal probability and the like, mechanism models output information of a variable triggering abnormal rule and the like), equipment suppliers, contact ways of field equipment responsible persons and the like. In the embodiment, the abnormal welding can be displayed more intuitively by generating the welding detection report, so that the tracking of the abnormal welding is convenient, and the processing efficiency of the subsequent processing process is improved.
It should be understood that although the various steps in the flow charts of fig. 2-7 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-7 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.
In one embodiment, as shown in fig. 8, there is provided a welding abnormality detection apparatus including:
the request obtaining module 801 is configured to receive a welding abnormality detection request and determine welding data corresponding to the welding abnormality detection request.
And a model feedback module 803, configured to feed back various preset welding anomaly detection models according to the welding anomaly detection request.
The information setting module 805 is configured to obtain model combination information and weight setting information corresponding to various preset welding anomaly detection models, where the model combination information is corresponding selection information of a preset welding anomaly detection model used in a welding anomaly detection process.
The model detection module 807 is configured to search a preset welding anomaly detection model specified by the model combination information from each preset welding anomaly detection model, input welding data into the preset welding anomaly detection model corresponding to the model combination information, and obtain each model detection result corresponding to the welding data.
And the anomaly detection module 809 is configured to receive multi-model welding anomaly detection results corresponding to the welding anomaly detection request according to the detection results of the models and the weight setting information.
In one embodiment, the information setting module 805 is specifically configured to: acquiring model combination information corresponding to various preset welding abnormity detection models; searching historical weight setting information ranking of model combination corresponding to the model combination information in historical data; ranking and feeding back a weight setting recommendation table according to historical weight setting information; and acquiring weight setting information fed back according to the weight setting recommendation table.
In one embodiment, the information setting module 805 is further configured to: obtaining model combination information corresponding to various preset welding abnormity detection models, and feeding back corresponding test welding data with result marks according to the model combination information; acquiring test weight setting data corresponding to the test welding data; acquiring test welding data and a multi-model welding abnormity test result corresponding to the test weight setting data through a preset welding abnormity detection model corresponding to the model combination information; feeding back a multi-mode welding abnormity test result; and acquiring weight setting information fed back according to the multi-model welding abnormity test result.
In one embodiment, the model feedback module 803 is specifically configured to: acquiring historical response time and historical recognition rate corresponding to various preset welding anomaly detection models; performing information labeling on various preset welding abnormity detection models according to historical response time and historical recognition rate; and various preset welding abnormity detection models are marked according to the welding abnormity detection request feedback information.
In one embodiment, the anomaly detection module 809 is specifically configured to: acquiring an abnormal detection weighted fusion result according to each model detection result and the weight setting information; and when the weighted fusion result of the abnormal detection is larger than or equal to the preset abnormal detection threshold value, judging that the multi-model welding abnormal detection result corresponding to the welding abnormal detection request is normal welding, and when the weighted fusion result of the abnormal detection is smaller than the preset abnormal detection threshold value, judging that the multi-model welding abnormal detection result corresponding to the welding abnormal detection request is abnormal welding.
In one embodiment, the system further comprises a report generation module for: when the multi-mode welding abnormity detection result is abnormal welding, generating a welding detection report of the multi-mode welding abnormity detection result; and feeding back a welding detection report.
For specific limitations of the welding abnormality detection device, reference may be made to the above limitations of the welding abnormality detection method, and details thereof are not repeated here. All or part of the modules in the welding abnormality detection device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store traffic forwarding data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a welding anomaly detection method.
Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
receiving a welding abnormity detection request, and determining welding data corresponding to the welding abnormity detection request;
feeding back various preset welding abnormity detection models according to the welding abnormity detection request;
acquiring model combination information and weight setting information corresponding to various preset welding abnormity detection models, wherein the model combination information is corresponding selection information of the preset welding abnormity detection model used in the welding abnormity detection process;
searching preset welding abnormity detection models specified by model combination information from various preset welding abnormity detection models, inputting welding data into the preset welding abnormity detection models corresponding to the model combination information, and acquiring detection results of the models corresponding to the welding data;
and receiving a multi-model welding abnormity detection result corresponding to the welding abnormity detection request according to each model detection result and the weight setting information.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring model combination information corresponding to various preset welding abnormity detection models; searching historical weight setting information ranking of model combination corresponding to the model combination information in historical data; ranking and feeding back a weight setting recommendation table according to historical weight setting information; and acquiring weight setting information fed back according to the weight setting recommendation table.
In one embodiment, the processor, when executing the computer program, further performs the steps of: obtaining model combination information corresponding to various preset welding abnormity detection models, and feeding back corresponding test welding data with result marks according to the model combination information; acquiring test weight setting data corresponding to the test welding data; acquiring test welding data and a multi-model welding abnormity test result corresponding to the test weight setting data through a preset welding abnormity detection model corresponding to the model combination information; feeding back a multi-mode welding abnormity test result; and acquiring weight setting information fed back according to the multi-model welding abnormity test result.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring historical response time and historical recognition rate corresponding to various preset welding anomaly detection models; performing information labeling on various preset welding abnormity detection models according to historical response time and historical recognition rate; and various preset welding abnormity detection models are marked according to the welding abnormity detection request feedback information.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring an abnormal detection weighted fusion result according to each model detection result and the weight setting information; and when the weighted fusion result of the abnormal detection is larger than or equal to the preset abnormal detection threshold value, judging that the multi-model welding abnormal detection result corresponding to the welding abnormal detection request is normal welding, and when the weighted fusion result of the abnormal detection is smaller than the preset abnormal detection threshold value, judging that the multi-model welding abnormal detection result corresponding to the welding abnormal detection request is abnormal welding.
In one embodiment, the processor, when executing the computer program, further performs the steps of: when the multi-mode welding abnormity detection result is abnormal welding, generating a welding detection report of the multi-mode welding abnormity detection result; and feeding back a welding detection report.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
receiving a welding abnormity detection request, and determining welding data corresponding to the welding abnormity detection request;
feeding back various preset welding abnormity detection models according to the welding abnormity detection request;
acquiring model combination information and weight setting information corresponding to various preset welding abnormity detection models, wherein the model combination information is corresponding selection information of the preset welding abnormity detection model used in the welding abnormity detection process;
searching preset welding abnormity detection models specified by model combination information from various preset welding abnormity detection models, inputting welding data into the preset welding abnormity detection models corresponding to the model combination information, and acquiring detection results of the models corresponding to the welding data;
and receiving a multi-model welding abnormity detection result corresponding to the welding abnormity detection request according to each model detection result and the weight setting information.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring model combination information corresponding to various preset welding abnormity detection models; searching historical weight setting information ranking of model combination corresponding to the model combination information in historical data; ranking and feeding back a weight setting recommendation table according to historical weight setting information; and acquiring weight setting information fed back according to the weight setting recommendation table.
In one embodiment, the computer program when executed by the processor further performs the steps of: obtaining model combination information corresponding to various preset welding abnormity detection models, and feeding back corresponding test welding data with result marks according to the model combination information; acquiring test weight setting data corresponding to the test welding data; acquiring test welding data and a multi-model welding abnormity test result corresponding to the test weight setting data through a preset welding abnormity detection model corresponding to the model combination information; feeding back a multi-mode welding abnormity test result; and acquiring weight setting information fed back according to the multi-model welding abnormity test result.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring historical response time and historical recognition rate corresponding to various preset welding anomaly detection models; performing information labeling on various preset welding abnormity detection models according to historical response time and historical recognition rate; and various preset welding abnormity detection models are marked according to the welding abnormity detection request feedback information.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring an abnormal detection weighted fusion result according to each model detection result and the weight setting information; and when the weighted fusion result of the abnormal detection is larger than or equal to the preset abnormal detection threshold value, judging that the multi-model welding abnormal detection result corresponding to the welding abnormal detection request is normal welding, and when the weighted fusion result of the abnormal detection is smaller than the preset abnormal detection threshold value, judging that the multi-model welding abnormal detection result corresponding to the welding abnormal detection request is abnormal welding.
In one embodiment, the computer program when executed by the processor further performs the steps of: when the multi-mode welding abnormity detection result is abnormal welding, generating a welding detection report of the multi-mode welding abnormity detection result; and feeding back a welding detection report.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile memory may include Read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, or the like. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A welding anomaly detection method, the method comprising:
receiving a welding abnormity detection request, and determining welding data corresponding to the welding abnormity detection request;
feeding back various preset welding abnormity detection models according to the welding abnormity detection request;
acquiring model combination information and weight setting information corresponding to the various preset welding abnormity detection models, wherein the model combination information is corresponding selection information of the preset welding abnormity detection model used in the welding abnormity detection process;
searching preset welding abnormity detection models specified by the model combination information from the various preset welding abnormity detection models, inputting the welding data into the preset welding abnormity detection models specified by the model combination information, and acquiring each model detection result corresponding to the welding data;
and acquiring a multi-model welding abnormity detection result corresponding to the welding abnormity detection request according to each model detection result and the weight setting information.
2. The method according to claim 1, wherein the obtaining of the model combination information and the weight setting information corresponding to the various types of preset welding abnormality detection models comprises:
acquiring model combination information corresponding to the various preset welding abnormity detection models;
searching historical weight setting information ranking of the model combination corresponding to the model combination information in historical data;
setting a recommendation table according to the historical weight setting information ranking feedback weight;
and acquiring weight setting information fed back according to the weight setting recommendation table.
3. The method according to claim 1, wherein the obtaining of the model combination information and the weight setting information corresponding to the various types of preset welding abnormality detection models comprises:
acquiring model combination information corresponding to the various preset welding abnormity detection models;
feeding back corresponding test welding data with result marks according to the model combination information;
acquiring test weight setting data corresponding to the test welding data;
acquiring the test welding data and a multi-model welding abnormity test result corresponding to the test weight setting data through a preset welding abnormity detection model corresponding to the model combination information;
feeding back the multi-mode welding abnormity test result;
and acquiring weight setting information fed back according to the multimode welding abnormity test result.
4. The method according to claim 1, wherein the feeding back various types of preset welding anomaly detection models according to the welding anomaly detection request comprises:
acquiring historical response time and historical recognition rate corresponding to various preset welding anomaly detection models;
performing information labeling on the various preset welding abnormity detection models according to the historical response time and the historical recognition rate;
and various preset welding abnormity detection models are marked according to the welding abnormity detection request feedback information.
5. The method according to claim 1, wherein the obtaining of the multi-model welding anomaly detection result corresponding to the welding anomaly detection request according to the model detection results and the weight setting information comprises:
acquiring an abnormal detection weighted fusion result according to the detection results of the models and the weight setting information;
and when the weighted fusion result of the abnormal detection is larger than or equal to a preset abnormal detection threshold value, judging that the multi-model welding abnormal detection result corresponding to the welding abnormal detection request is normal welding, and when the weighted fusion result of the abnormal detection is smaller than the preset abnormal detection threshold value, judging that the multi-model welding abnormal detection result corresponding to the welding abnormal detection request is abnormal welding.
6. The method according to claim 1, wherein after obtaining the multi-mode welding anomaly detection result corresponding to the welding anomaly detection request according to the model detection results and the weight setting information, the method further comprises:
when the multi-mode welding abnormity detection result is abnormal welding, generating a welding detection report of the multi-mode welding abnormity detection result;
and feeding back the welding detection report.
7. A welding anomaly detection device, said device comprising:
the request acquisition module is used for receiving a welding abnormity detection request and determining welding data corresponding to the welding abnormity detection request;
the model feedback module is used for feeding back various preset welding abnormity detection models according to the welding abnormity detection request;
the information setting module is used for acquiring model combination information and weight setting information corresponding to various preset welding abnormity detection models, wherein the model combination information is corresponding selection information of the preset welding abnormity detection models used in the welding abnormity detection process;
the model detection module is used for searching preset welding abnormity detection models specified by the model combination information from the various preset welding abnormity detection models, inputting the welding data into the preset welding abnormity detection models corresponding to the model combination information, and acquiring each model detection result corresponding to the welding data;
and the abnormality detection module is used for acquiring a multi-model welding abnormality detection result corresponding to the welding abnormality detection request according to the detection results of the models and the weight setting information.
8. The apparatus of claim 7, wherein the information setting module is specifically configured to:
acquiring model combination information corresponding to the various preset welding abnormity detection models;
searching historical weight setting information ranking of the model combination corresponding to the model combination information in historical data;
setting a recommendation table according to the historical weight setting information ranking feedback weight;
and acquiring weight setting information fed back according to the weight setting recommendation table.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110228624.9A CN113076350B (en) | 2021-03-02 | 2021-03-02 | Welding abnormality detection method, welding abnormality detection device, computer device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110228624.9A CN113076350B (en) | 2021-03-02 | 2021-03-02 | Welding abnormality detection method, welding abnormality detection device, computer device, and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113076350A true CN113076350A (en) | 2021-07-06 |
| CN113076350B CN113076350B (en) | 2024-05-07 |
Family
ID=76609631
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110228624.9A Active CN113076350B (en) | 2021-03-02 | 2021-03-02 | Welding abnormality detection method, welding abnormality detection device, computer device, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113076350B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114178653A (en) * | 2021-12-23 | 2022-03-15 | 唐山松下产业机器有限公司 | Welding quality detection method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106156170A (en) * | 2015-04-16 | 2016-11-23 | 北大方正集团有限公司 | The analysis of public opinion method and device |
| CN108898230A (en) * | 2018-05-24 | 2018-11-27 | 华为技术有限公司 | A kind of device management method and management server |
| CN109063886A (en) * | 2018-06-12 | 2018-12-21 | 阿里巴巴集团控股有限公司 | A kind of method for detecting abnormality, device and equipment |
| CN110889153A (en) * | 2018-08-20 | 2020-03-17 | 西安海平方网络科技有限公司 | Model adjusting method and device, computer equipment and storage medium |
| CN111069736A (en) * | 2019-12-27 | 2020-04-28 | 唐山松下产业机器有限公司 | Storage medium, welding equipment, welding abnormity detection method and device |
| CN111325463A (en) * | 2020-02-18 | 2020-06-23 | 深圳前海微众银行股份有限公司 | Data quality detection method, device, equipment and computer readable storage medium |
| WO2020140678A1 (en) * | 2019-01-04 | 2020-07-09 | 深圳壹账通智能科技有限公司 | Abnormal application detection method and apparatus, and computer device and storage medium |
-
2021
- 2021-03-02 CN CN202110228624.9A patent/CN113076350B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106156170A (en) * | 2015-04-16 | 2016-11-23 | 北大方正集团有限公司 | The analysis of public opinion method and device |
| CN108898230A (en) * | 2018-05-24 | 2018-11-27 | 华为技术有限公司 | A kind of device management method and management server |
| CN109063886A (en) * | 2018-06-12 | 2018-12-21 | 阿里巴巴集团控股有限公司 | A kind of method for detecting abnormality, device and equipment |
| CN110889153A (en) * | 2018-08-20 | 2020-03-17 | 西安海平方网络科技有限公司 | Model adjusting method and device, computer equipment and storage medium |
| WO2020140678A1 (en) * | 2019-01-04 | 2020-07-09 | 深圳壹账通智能科技有限公司 | Abnormal application detection method and apparatus, and computer device and storage medium |
| CN111069736A (en) * | 2019-12-27 | 2020-04-28 | 唐山松下产业机器有限公司 | Storage medium, welding equipment, welding abnormity detection method and device |
| CN111325463A (en) * | 2020-02-18 | 2020-06-23 | 深圳前海微众银行股份有限公司 | Data quality detection method, device, equipment and computer readable storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114178653A (en) * | 2021-12-23 | 2022-03-15 | 唐山松下产业机器有限公司 | Welding quality detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113076350B (en) | 2024-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7499777B2 (en) | Diagnostic and prognostic method and system | |
| JP5808605B2 (en) | Abnormality detection / diagnosis method and abnormality detection / diagnosis system | |
| CN109669844B (en) | Equipment fault processing method, device, equipment and storage medium | |
| CN110875851B (en) | Underground cable fault early warning method and device | |
| CN111338836A (en) | Method, device, computer equipment and storage medium for processing fault data | |
| KR102306269B1 (en) | Method and apparatus for real-time arc-welding defect detection and classification | |
| US20200261997A1 (en) | Systems and methods providing pattern recognition and data analysis in welding and cutting | |
| CN110798245B (en) | Underground cable fault early warning method and device based on single model | |
| CN110868241A (en) | Underground cable fault early warning method and device based on multiple models | |
| JP2006135412A (en) | Remote supervisory system | |
| CN110825923A (en) | Underground cable fault repairing method and device based on single model | |
| CN110866634A (en) | Underground cable fault early warning method and device based on model selection | |
| Harichandran et al. | Equipment activity recognition and early fault detection in automated construction through a hybrid machine learning framework | |
| CN113076350A (en) | Welding abnormity detection method and device, computer equipment and storage medium | |
| CN113283620B (en) | Operation and maintenance method, device, equipment and storage medium based on artificial intelligence | |
| CN113093584B (en) | Welding abnormity detection method and device, computer equipment and storage medium | |
| CN111324375A (en) | Code management method and device, computer equipment and storage medium | |
| CN112183555B (en) | Method and system for detecting welding quality, electronic device and storage medium | |
| CN113222531A (en) | Data storage and monitoring method, system, computer equipment and storage medium | |
| Zhang et al. | Pace: Prompting and augmentation for calibrated confidence estimation with gpt-4 in cloud incident root cause analysis | |
| CN117240527B (en) | Network security risk prevention system and method | |
| CN110889357B (en) | Underground cable fault detection method and device based on labeling area | |
| CN112711605B (en) | Fault analysis method, device, computer equipment and storage medium | |
| CN116381419A (en) | Transmission line fault processing method, device, computer equipment and storage medium | |
| CN110851670A (en) | Underground cable fault repairing method and device |
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 |