CN116475651A - Intelligent edge control method for welding overhaul and intelligent welding equipment - Google Patents
Intelligent edge control method for welding overhaul and intelligent welding equipment Download PDFInfo
- Publication number
- CN116475651A CN116475651A CN202310235847.7A CN202310235847A CN116475651A CN 116475651 A CN116475651 A CN 116475651A CN 202310235847 A CN202310235847 A CN 202310235847A CN 116475651 A CN116475651 A CN 116475651A
- Authority
- CN
- China
- Prior art keywords
- data
- welding
- intelligent
- control method
- overhaul
- 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
Links
- 238000003466 welding Methods 0.000 title claims abstract description 121
- 238000000034 method Methods 0.000 title claims abstract description 108
- 230000008569 process Effects 0.000 claims abstract description 59
- 238000013210 evaluation model Methods 0.000 claims abstract description 17
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 14
- 238000000605 extraction Methods 0.000 claims abstract description 14
- 238000010801 machine learning Methods 0.000 claims abstract description 9
- 238000012797 qualification Methods 0.000 claims abstract description 9
- 238000011156 evaluation Methods 0.000 claims abstract description 7
- 238000012544 monitoring process Methods 0.000 claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 238000010276 construction Methods 0.000 claims abstract description 5
- 238000011158 quantitative evaluation Methods 0.000 claims abstract description 4
- 238000012360 testing method Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 12
- 238000003066 decision tree Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 10
- 239000000463 material Substances 0.000 claims description 8
- 238000007637 random forest analysis Methods 0.000 claims description 8
- 238000007689 inspection Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 abstract description 8
- 238000012423 maintenance Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 230000007704 transition Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000006247 magnetic powder Substances 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- B23K37/00—Auxiliary devices or processes, not specially adapted to a procedure covered by only one of the preceding main groups
- B23K37/02—Carriages for supporting the welding or cutting element
- B23K37/0252—Steering means
-
- 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
- B23K31/02—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 soldering or welding
-
- 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
- B23K37/00—Auxiliary devices or processes, not specially adapted to a procedure covered by only one of the preceding main groups
-
- 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
- B23K37/00—Auxiliary devices or processes, not specially adapted to a procedure covered by only one of the preceding main groups
- B23K37/02—Carriages for supporting the welding or cutting element
- B23K37/0247—Driving means
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses an intelligent edge control method for welding overhaul and intelligent welding equipment, wherein the intelligent edge control method comprises the following steps: various data generated in the welding process are obtained, the data are matched and classified from multiple dimensions by using a machine learning algorithm to finish feature extraction, a prediction evaluation model facing to process quantitative evaluation is established for the data after feature extraction, the prediction evaluation model is corrected by using a historical test result, the prediction evaluation model is used for carrying out real-time calculation evaluation on construction data of a welder through real-time monitoring and prediction, a dynamic process parameter range taking qualification as a result is obtained, and then active intervention is carried out on output parameters of current welding equipment. The intelligent edge control method and the intelligent welding equipment provided by the invention can actively interfere with the output parameters of the current welding machine, and avoid defects and quality problems caused by human factors.
Description
Technical Field
The invention relates to the technical field of intelligent welding maintenance, in particular to an intelligent edge control method for welding maintenance and intelligent welding equipment. Intelligent edge control method for welding overhaul and intelligent welding equipment
Background
The intelligent welding maintenance technology is a technical system for realizing automation, digitization and intellectualization of welding maintenance by utilizing modern information technology and intelligent technology on the basis of the traditional welding maintenance technology. At present, the intelligence can utilize technologies such as laser rangefinder, visual identification, realizes the real-time detection to the work piece surface in the welding maintenance process, makes welding process more stable and accurate. The existing welding process parameters are the welding process taking the qualitative result as the guide, and the welding parts can be classified into a plurality of assessment results of qualification, qualification with defects and disqualification with defects by a classification method only by adopting nondestructive inspection and physicochemical inspection after the welder is completely constructed.
In the conventional manual welding operation process, quality defects and operation risks are often caused by human factors, so that the intelligence of autonomous parameter adjustment of welding machine equipment is needed to be improved. In the past intelligent welding machine, the focus is on the engineering of sensor acquisition and monitoring, and in the welding process data collection, only current and voltage time domain data in the process are collected, the welding machine output cannot be actively interfered, and the intelligent degree is low.
The voltage and the current of the existing process card of the welding technology are all range values for different welding methods, in theory, the welding quality can ensure the quality requirement as long as the voltage and the current range values on the process card are followed, but welding engineers at different levels and welding positions in different scenes in the actual process overhaul operation are brands of different welding machines, the welding operation is an uncontrollable variable, the welding quality can be influenced, and the ultrasonic, magnetic powder, hardness and metallographic examination in the historical nondestructive detection report can be referred.
The above disclosure of background art is only for aiding in understanding the inventive concept and technical solution of the present invention, and it does not necessarily belong to the prior art of the present patent application, nor does it necessarily give technical teaching; the above background should not be used to assess the novelty and creativity of the present application without explicit evidence that the above-mentioned content was disclosed prior to the filing date of the present patent application.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides an intelligent edge control method for welding overhaul and intelligent welding equipment, and the specific technical scheme is as follows:
in one aspect, an edge intelligent control method for welding overhaul is provided, which comprises the following steps:
various data generated in the welding process are obtained, the data are matched and classified from multiple dimensions by using a machine learning algorithm to finish feature extraction, a prediction evaluation model facing to process quantitative evaluation is established for the data after feature extraction, the prediction evaluation model is corrected by using a historical test result, the prediction evaluation model is used for carrying out real-time calculation evaluation on construction data of a welder through real-time monitoring and prediction, a dynamic process parameter range taking qualification as a result is obtained, and then active intervention is carried out on output parameters of current welding equipment.
Further, the predictive evaluation model establishes a big data system of a complete welding process, and according to the big data system, data are matched and classified from a plurality of dimensions which are not mutually interfered, and then a training data set is formed by taking the dimensions as characteristic values.
Further, the plurality of dimensions includes welding engineers, welding joints and materials, environmental factors and inspection results, welding equipment model, and welding process.
Further, after extracting the data characteristics of the continuous welding process, constructing a decision tree by using Gini index training; multiple training is performed to generate multiple decision trees.
Further, the decision tree training is structured as a random forest to optimize the predictive assessment model.
Further, when there is a partial null value, an abnormal value or data exceeding a threshold value range in the acquired data, a data patch algorithm is required to patch the data, and the data patch algorithm includes a data gaussian smoothing denoising method, an interpolation data patch method and a threshold value method filtering.
Further, acquiring data generated in the welding process by using a sensor and a data acquisition device; before the feature extraction is performed on the data, data preprocessing is required, wherein when the sample acquisition frequencies of all the data sources are different, correction and alignment of time stamps are performed according to input time specifications during the data preprocessing, so that the time sequence data input of the predictive evaluation model is ensured to have a unified standard.
Further, the data generated during the welding process includes ambient temperature, welder output voltage, welder current, welder displacement, and welder movement speed.
Further, the dynamic process parameter range comprises a reasonable voltage range, and the welding equipment automatically adjusts the current output voltage according to the reasonable voltage range obtained in real time.
On the other hand, an intelligent welding device is provided, which comprises a welding machine controller, a welding machine voltage output device and a data acquisition device, wherein the welding machine controller controls the welding machine voltage output device through the edge intelligent control method, and the data acquisition device acquires various data of a welding machine and feeds the data back to the welding machine controller in real time.
Compared with the prior art, the invention has the following advantages: the intelligent of autonomous parameter adjustment of welding machine equipment is improved, active intervention is carried out on the output parameters of the current welding machine, and defects and quality problems caused by human factors are avoided.
Drawings
Fig. 1 is a schematic diagram of voltage and current raw data in an edge intelligent control method for welding maintenance according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a heat input value raw data curve in an edge intelligent control method for welding overhaul, which is provided by the embodiment of the invention;
fig. 3 is a schematic diagram of voltage and current data after preprocessing in the edge intelligent control method for welding maintenance according to the embodiment of the present invention;
FIG. 4 is a schematic diagram of a random forest assessment qualification confidence interval curve in an edge intelligent control method for welding overhaul, which is provided by the embodiment of the invention;
fig. 5 is a schematic diagram of discretization of data features in an edge intelligent control method for welding overhaul, which is provided by an embodiment of the invention;
FIG. 6 is a schematic diagram of a random forest prediction result in an edge intelligent control method for welding overhaul provided by an embodiment of the invention;
fig. 7 is a schematic structural diagram of an intelligent welding device according to an embodiment of the present invention.
Wherein, the reference numerals are as follows: 1-a characteristic value of a qualified process threshold value of each stage, 2-a central fit line of a prediction process, 3-a qualified process characteristic fluctuation transition fit line and 4-95% confidence interval.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion.
In one embodiment of the invention, an edge intelligent control method for welding overhaul is provided, which comprises the following steps:
various data generated in the welding process are obtained, the data are matched and classified from multiple dimensions by using a machine learning algorithm to finish feature extraction, a prediction evaluation model facing to process quantitative evaluation is established for the data after feature extraction, the prediction evaluation model is corrected by using a historical test result, the prediction evaluation model is used for carrying out real-time calculation evaluation on construction data of a welder through real-time monitoring and prediction, a dynamic process parameter range taking qualification as a result is obtained, and then active intervention is carried out on output parameters of current welding equipment. The dynamic process parameter range comprises a reasonable voltage range, and the welding equipment automatically adjusts the current output voltage according to the reasonable voltage range obtained in real time.
In a preferred embodiment, the edge intelligent control method specifically comprises the following steps:
s1, data acquisition: sensors and data acquisition devices are used to acquire data during the welding process, such as temperature, voltage, current, displacement, speed, etc.
S2, data preprocessing: and (3) carrying out preprocessing operations such as cleaning, denoising, outlier processing, data alignment and the like on the collected original data so as to improve the quality and reliability of the data.
S3, feature extraction: the data in the welding process is converted into numerical features that can be used in machine learning algorithms by feature extraction techniques, for example, using wavelet transforms, fourier transforms, time domain feature extraction, and the like.
S4, data modeling: modeling the data after feature extraction by using a machine learning algorithm, for example, performing tasks such as classification, clustering, regression and the like by using algorithms such as a neural network, a decision tree, a support vector machine, a random forest and the like.
S5, model optimization: optimizing modeling results through technologies such as parameter adjustment, feature selection and model fusion, and improving prediction capacity and generalization capacity of the model.
S6, model application: the optimized machine learning model is applied to the actual welding process, historical data of a welder are calculated in real time through real-time monitoring and prediction, and the output parameters of the welder are actively interfered according to the condition data of a person (welding engineer), a machine (welding brand), materials (welding joint and welding material), a method (welding process), a ring (environmental factors and inspection results) and the like of the current welding work, so that defects and quality problems caused by human factors are avoided.
It should be noted that the analysis and processing of data during welding requires a certain knowledge of the welding process and data science skills. At the same time, reasonable selection and optimization are needed for selection and parameter adjustment of the machine learning algorithm so as to fully exert the advantages of the algorithm and avoid the problems of over fitting, under fitting and the like.
In step S2, the data preprocessing mainly includes data noise removal, numerical smoothing and abnormal data analysis, and provides a good data analysis environment for the prediction model. For example, the sampled data usually has a partial null value (non-working state), an abnormal value or data exceeding a threshold range (such as current-voltage abrupt change in an ignition high-frequency state), and for such abnormal data, a data-based interpolation algorithm can be adopted, which includes mathematical methods such as a data gaussian smoothing denoising method, an interpolation data interpolation method, a threshold value method filtering method and the like, so as to ensure the integrity and the accuracy of the data. The sample collection frequency of each data source can be different according to different data collection devices, and the correction and the alignment of the time stamp can be carried out according to the input time standard during the data preprocessing so as to ensure that the time sequence data input of the prediction model has a unified standard. The collected historical welding process data, such as the data in fig. 1 and 2, are subjected to data preprocessing to obtain a data curve similar to the data curve in fig. 3.
In step S4, the method specifically includes the following steps:
s41, screening out welding process data with qualified results
S42, classifying five dimensions of a person (same operator), a machine (same welding machine), a material (same welding material), a method (same welding process) and a ring (environment temperature variable), and forming a training data set by taking the five dimensions which are not mutually interfered as characteristic values.
S43, discretizing the continuous welding process data according to the characteristic values in the step S42, and constructing a decision tree by using Gini index training, wherein the characteristic values are randomly selected. The Gini index represents the probability that a selected sample in the sample set is misclassified, and its calculation formula is as follows:
p k representing the probability that the selected sample belongs to the k-class, then this sample is misclassifiedThe probability is (1-p) k ) There are K categories in the sample set, and a randomly selected sample can belong to any of the K categories, thus summing the categories. The smaller the Gini index, the smaller the probability that the selected sample in the collection is misclassified, that is, the higher the purity of the collection, and conversely, the less pure the collection.
S44, training for multiple times according to the steps S42 and S43 to generate multiple decision trees
S45, training the decision tree into a random forest to obtain an evaluation model taking 'people, machines, materials, methods and rings' as characteristic dimensions.
The model is built, and not only point-to-point evaluation information but also an evaluation interval is to be obtained. At the time of process prediction, we obtain not only an evaluation value of the qualified process at the current time, but also intervals of the lowest value and the highest value such as the qualification threshold.
The continuous welding process data are subjected to characteristic discretization, random forest classification is adopted, and referring to fig. 4 to 6, random forest prediction results are shown in the following graphs, wherein red stars are characteristic values 1 of qualified process thresholds in each stage. The yellow line is the center fit line 2 of the prediction process, i.e. the qualifying process feature values are normally distributed around the line. The black line is a qualified process characteristic fluctuation transition fitting line 3, namely, transition fitting is carried out on the fluctuation change of the qualified process characteristic value. The red background is a 95% confidence interval 4, that is, for each time x, the corresponding qualified process feature value y changes, the red background is the upper and lower limits of the qualified threshold, the maximum is not more than the upper limit, and the minimum is not more than the lower limit.
The edge intelligent control method for welding overhaul provided by the invention is characterized in that quantitative results are used as guidance, data of a welding process of a welder is modeled by a machine learning method, a historical inspection result is used for correcting a model, a model which is established by five dimensional variables of people, machines, materials, methods and rings and faces to process quantitative assessment is finally obtained, construction data of the welder is calculated and assessed in real time by real-time monitoring and prediction, a dynamic technological parameter range taking qualification as a result is obtained, active intervention is carried out on output parameters of the welder, and defects and quality problems caused by human factors are avoided.
The embodiment of the invention also provides intelligent welding equipment, which comprises a welding machine controller, a welding machine voltage output device and a data acquisition device, wherein the welding machine controller controls the welding machine voltage output device through the edge intelligent control method, and the data acquisition device acquires various data of a welding machine and feeds the data back to the welding machine controller in real time. . The idea of the embodiment of the intelligent welding device belongs to the same idea as the working process of the edge intelligent control method in the embodiment, and the whole content of the embodiment of the detection method is incorporated into the embodiment of the device by way of full-text reference, and is not repeated.
When the existing welding machine is intelligently upgraded, universal automatic regulation and control equipment is added on the basis of intelligent acquisition, and output voltage is automatically regulated. The principle of the original welder for controlling voltage/current is that a knob potentiometer on a control panel is regulated to output a low-voltage direct current, after the controller on the control panel detects the voltage, the voltage information is transmitted to a main control board of the welder through a CAN message, and a driving circuit generates corresponding voltage/current. After transformation, referring to fig. 6, the welder transformation controller calculates voltage/current information issued by the cloud as low-voltage direct current through a corresponding relation, and issues a command for outputting the voltage to the AO module through a 485 protocol. After the AO module receives the command, the original knob potentiometer is replaced to output low-voltage direct current to a controller on a control panel, namely the position of a welder display panel, voltage information is sent to a welder main control panel through a CAN message, and a driving circuit generates corresponding voltage/current.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present invention are directly or indirectly applied to other related technical fields, which are also included in the scope of the present invention.
Claims (10)
1. An intelligent edge control method for welding overhaul is characterized by comprising the following steps:
various data generated in the welding process are obtained, the data are matched and classified from multiple dimensions by using a machine learning algorithm to finish feature extraction, a prediction evaluation model facing to process quantitative evaluation is established for the data after feature extraction, the prediction evaluation model is corrected by using a historical test result, the prediction evaluation model is used for carrying out real-time calculation evaluation on construction data of a welder through real-time monitoring and prediction, a dynamic process parameter range taking qualification as a result is obtained, and then active intervention is carried out on output parameters of current welding equipment.
2. The method for intelligent edge control for welding overhaul according to claim 1, wherein the predictive evaluation model establishes a big data system of a complete welding process, and according to the big data system, data are matched and classified from a plurality of dimensions which do not interfere with each other, and a training data set is formed by taking the dimensions as characteristic values.
3. The edge intelligence control method for weld service of claim 1, wherein the plurality of dimensions includes a welding engineer, a weld joint and a welding material, environmental factors and inspection results, a welding equipment model, and a welding process.
4. The edge intelligent control method for welding overhaul according to claim 1, wherein after extracting data features of a continuous welding process, a decision tree is constructed by using Gini index training; multiple training is performed to generate multiple decision trees.
5. The edge intelligence control method for weld overhaul of claim 4, wherein the decision tree training is structured as a random forest to optimize the predictive assessment model.
6. The method according to claim 1, wherein when there is a partial null value, an abnormal value or data exceeding a threshold value range in the acquired data, a data patch algorithm is required to patch the data, the data patch algorithm including a data gaussian smoothing denoising method, an interpolation data patch method and a threshold value method filtering.
7. The edge intelligence control method for weld inspection of claim 6, wherein data generated during welding is acquired using sensors and data acquisition devices; before the feature extraction is performed on the data, data preprocessing is required, wherein when the sample acquisition frequencies of all the data sources are different, correction and alignment of time stamps are performed according to input time specifications during the data preprocessing, so that the time sequence data input of the predictive evaluation model is ensured to have a unified standard.
8. The method of claim 1, wherein the data generated during the welding process includes ambient temperature, welder output voltage, welder current, welder displacement, and welder movement speed.
9. The edge intelligent control method for welding overhaul as claimed in claim 1, wherein the dynamic process parameter range includes a reasonable voltage range, and the welding equipment automatically adjusts the current output voltage according to the reasonable voltage range obtained in real time.
10. An intelligent welding device, comprising a welding machine controller, a welding machine voltage output device and a data acquisition device, wherein the welding machine controller controls the welding machine voltage output device through the edge intelligent control method according to any one of claims 1-9, and the data acquisition device acquires various data of a welding machine and feeds the data back to the welding machine controller in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310235847.7A CN116475651A (en) | 2023-03-13 | 2023-03-13 | Intelligent edge control method for welding overhaul and intelligent welding equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310235847.7A CN116475651A (en) | 2023-03-13 | 2023-03-13 | Intelligent edge control method for welding overhaul and intelligent welding equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116475651A true CN116475651A (en) | 2023-07-25 |
Family
ID=87216786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310235847.7A Pending CN116475651A (en) | 2023-03-13 | 2023-03-13 | Intelligent edge control method for welding overhaul and intelligent welding equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116475651A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118237825A (en) * | 2024-05-28 | 2024-06-25 | 凯沃智能装备(青岛)有限公司 | Welding machine method and welding robot based on artificial intelligence |
-
2023
- 2023-03-13 CN CN202310235847.7A patent/CN116475651A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118237825A (en) * | 2024-05-28 | 2024-06-25 | 凯沃智能装备(青岛)有限公司 | Welding machine method and welding robot based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE102018215826B4 (en) | Robot system and workpiece gripping method | |
| DE102017010799B4 (en) | Machine learning device for learning a processing sequence of a robot system with a plurality of laser processing robots, associated robot system and machine learning method for learning a processing sequence of the robot system with a plurality of laser processing robots | |
| DE102017008475B4 (en) | MACHINE LEARNING DEVICE, ROBOT SYSTEM AND MACHINE LEARNING METHOD FOR LEARNING A ROBOT OPERATING PROGRAM | |
| US8781982B1 (en) | System and method for estimating remaining useful life | |
| CN108890652B (en) | Transformer substation inspection robot and transformer substation equipment inspection method | |
| CN116475651A (en) | Intelligent edge control method for welding overhaul and intelligent welding equipment | |
| CN117767271A (en) | Electric power emergency automatic management system | |
| CN115994308B (en) | Numerical control machine tool fault identification method, system, equipment and medium based on meta learning | |
| CN108931621B (en) | Zinc ore grade soft measurement method based on process texture characteristics | |
| DE102021204943A1 (en) | META-SCHOOLED EVOLUTIONAL STRATEGY BLACKBOX OPTIMIZATION CLASSIFIER | |
| EP4258179A1 (en) | Method and computer program for monitoring an artificial intelligence | |
| Biradar et al. | Intelligent Control Systems for Industrial Automation and Robotics | |
| DE102022213603A1 (en) | Method, system and medium for papermaking quality evaluation | |
| CN114266286B (en) | Online detection method and device for welding process information | |
| CN115129003A (en) | Automatic production line intelligent monitoring system based on self-learning time-varying digital twin | |
| CN113902710A (en) | Method and system for detecting surface defects of industrial parts based on anomaly detection algorithm | |
| CN114859821A (en) | Self-detection, self-analysis and self-adaptive numerical control machine tool fuzzy control system | |
| CN116092014A (en) | Intelligent inspection control method and system based on Internet of things equipment | |
| JP2019003545A (en) | Operation support device, operation support method, operation support program, and storage medium | |
| CN110533107A (en) | Grad enhancement type Softmax classifier, training signal production method and its application | |
| CN114764538B (en) | Equipment sound signal mode identification method | |
| KR20210157253A (en) | Apparatus and method for learning quality estimation model of welding, and estimation apparatus using the model | |
| CN115373383A (en) | Autonomous obstacle avoidance method and device for garbage recovery unmanned boat and related equipment | |
| CN207866282U (en) | One kind being based on unpiloted multiple-sensor integration control and monitoring system | |
| CN118311935B (en) | Household automatic production control system and method |
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 |