CN117600701A - Online monitoring system and control method for friction stir welding process - Google Patents
Online monitoring system and control method for friction stir welding process Download PDFInfo
- Publication number
- CN117600701A CN117600701A CN202311873226.8A CN202311873226A CN117600701A CN 117600701 A CN117600701 A CN 117600701A CN 202311873226 A CN202311873226 A CN 202311873226A CN 117600701 A CN117600701 A CN 117600701A
- Authority
- CN
- China
- Prior art keywords
- temperature
- welding
- friction stir
- module
- stir welding
- 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 234
- 238000000034 method Methods 0.000 title claims abstract description 151
- 230000008569 process Effects 0.000 title claims abstract description 118
- 238000012544 monitoring process Methods 0.000 title claims abstract description 27
- 238000003756 stirring Methods 0.000 title claims description 103
- 238000011156 evaluation Methods 0.000 claims abstract description 23
- 239000000463 material Substances 0.000 claims abstract description 6
- 238000003825 pressing Methods 0.000 claims description 55
- 238000009529 body temperature measurement Methods 0.000 claims description 44
- 230000006870 function Effects 0.000 claims description 27
- 239000013307 optical fiber Substances 0.000 claims description 26
- 230000005855 radiation Effects 0.000 claims description 26
- 230000007246 mechanism Effects 0.000 claims description 22
- 229910000838 Al alloy Inorganic materials 0.000 claims description 19
- 238000013528 artificial neural network Methods 0.000 claims description 16
- 239000004973 liquid crystal related substance Substances 0.000 claims description 11
- 230000004927 fusion Effects 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000013461 design Methods 0.000 claims description 8
- 235000017166 Bambusa arundinacea Nutrition 0.000 claims description 7
- 235000017491 Bambusa tulda Nutrition 0.000 claims description 7
- 241001330002 Bambuseae Species 0.000 claims description 7
- 235000015334 Phyllostachys viridis Nutrition 0.000 claims description 7
- 239000011425 bamboo Substances 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 238000013210 evaluation model Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000007500 overflow downdraw method Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 2
- 229920000915 polyvinyl chloride Polymers 0.000 description 7
- 239000004800 polyvinyl chloride Substances 0.000 description 7
- 230000001105 regulatory effect Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 229910052782 aluminium Inorganic materials 0.000 description 3
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- 238000002834 transmittance Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000001931 thermography Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000005457 Black-body radiation Effects 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 229910000861 Mg alloy Inorganic materials 0.000 description 1
- 239000004614 Process Aid Substances 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 229910045601 alloy Inorganic materials 0.000 description 1
- 239000000956 alloy Substances 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 239000007769 metal material Substances 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004861 thermometry Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- B23K31/00—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups
- B23K31/12—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups relating to investigating the properties, e.g. the weldability, of materials
- B23K31/125—Weld quality monitoring
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K20/00—Non-electric welding by applying impact or other pressure, with or without the application of heat, e.g. cladding or plating
- B23K20/12—Non-electric welding by applying impact or other pressure, with or without the application of heat, e.g. cladding or plating the heat being generated by friction; Friction welding
- B23K20/122—Non-electric welding by applying impact or other pressure, with or without the application of heat, e.g. cladding or plating the heat being generated by friction; Friction welding using a non-consumable tool, e.g. friction stir 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
- B23K20/00—Non-electric welding by applying impact or other pressure, with or without the application of heat, e.g. cladding or plating
- B23K20/26—Auxiliary equipment
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Quality & Reliability (AREA)
- Pressure Welding/Diffusion-Bonding (AREA)
Abstract
The system comprises a vision module, a temperature measuring module, a feedback execution module and a performance prediction and evaluation module, wherein the vision module is used for collecting image information and transmitting the collected image information to the feedback execution module, the temperature measuring module is used for collecting real-time temperature and transmitting the real-time temperature to the feedback execution module, the feedback execution module is used for material welding and process parameter adjustment, and integrating and transmitting all acquired information to the performance prediction and evaluation module, and the performance prediction and evaluation module analyzes the acquired information to obtain a welding joint strength prediction evaluation result. The invention ensures that the temperature fluctuation along the welding line direction is in a controllable range by comparing and controlling the real-time temperature data monitoring of the welding line and the peak temperature of the temperature field, and greatly enhances the strength stability of the welding structure.
Description
Technical Field
The invention relates to the technical field of metal material welding, in particular to an online monitoring system and a control method for a friction stir welding process.
Background
With the development of intellectualization, precision and light weight in the manufacturing fields of aerospace, rail transit, ships and the like, aluminum alloy has become a main choice of lightweight structural design materials due to the characteristics of high specific strength, good corrosion resistance, excellent processability, high plasticity, recycling and the like. The friction stir welding technology is widely used in aluminum alloy welding, has the advantages of good mechanical property of welded joints of welded parts, low cost, high efficiency, green and pollution-free properties and the like, and has outstanding advantages in welding light-weight alloys such as aluminum, magnesium alloy and the like. Two key parameters affecting the quality of the welded joint in friction stir welding: the heat input and the pressure are taken as one of important factors, and the accurate acquisition of the welding temperature value has key technical significance in the aspect of realizing high-performance stable welding joints.
Common temperature detection methods are mainly divided into two types, namely contact temperature measurement and non-contact temperature measurement. In the non-contact temperature measurement method, infrared temperature measurement is widely applied, and the characteristics of the method include rapid response speed, convenient operation and the like. In the friction stir welding process, infrared temperature measurement has significant advantages and can be used for realizing autonomous control of the welding process. The emissivity of a temperature measurement target in the conventional infrared temperature measurement process is generally regarded as a constant, and the temperature of the temperature measurement target is determined by measuring the radiation intensity of the target according to the Planck blackbody radiation law. However, in the infrared temperature measurement of aluminum alloy, emissivity varies with temperature, so that the conventional infrared temperature measurement method cannot meet ideal temperature measurement accuracy. On the other hand, the contact type temperature measuring method, such as thermocouple temperature measurement, has the advantage of measuring accuracy. However, the method has the defects of damage to the surface of the plate, complex operation, high cost, incapability of detecting the temperature of the welding process in real time, and the like. Therefore, one of the key technical problems faced by the current friction stir welding process is to find a convenient, effective, follow-up and accurate temperature detection method in the aluminum alloy friction stir welding process. In the prior art, for example, the disclosed invention patent CN111854968A proposes a method for measuring the temperature of the same aluminum ingot by two infrared thermometers with different emissivity, and establishing simultaneous equations according to the two measured different temperature values and the respective emissivity to obtain the actual temperature of the measured aluminum ingot. However, this method does not consider the problem of aluminum alloy emissivity varying with temperature. On the other hand, the invention patent CN116329299a obtains the actual strip temperature by contact temperature measurement, then inputs the temperature into an infrared thermometer to automatically calculate emissivity, and records the calculated emissivity parameter. Although this approach solves the problem of dynamic calculation of emissivity, the case of aluminum alloy emissivity variation is not considered. In addition, the invention patent CN115060376a proposes an aluminum alloy temperature field measurement method based on infrared thermal imaging and iterative algorithm, which calculates a stable emissivity field from data obtained by infrared thermal imaging and thermocouple measurement, and obtains the temperature of the measured target by using the field and radiation intensity. However, this method cannot adjust the friction stir welding process parameters in real time. Therefore, the method for realizing the on-line monitoring and parameter control of the high-performance stable friction stir welding process has important significance for ensuring the consistency of the strength of the welding joint along the welding line direction.
Disclosure of Invention
In order to solve the problems that in the prior art, the accuracy requirement for detecting the temperature of a plate is high in the welding process, the temperature measurement of the existing aluminum alloy plate is difficult, and the error is large, the invention provides an online monitoring system and a control method for a stirring friction welding process. And the temperature difference value is input into the temperature intelligent regulation model to obtain the regulating quantity of the downward pressure quantity of the shaft shoulder. The process auxiliary computer sends an instruction to the parameter adjusting mechanism according to the pressing quantity adjusting quantity, and real-time regulation and control of the welding process are achieved, so that stable welding of the aluminum alloy plates is ensured. Meanwhile, the acquired temperature data, technological parameters in the welding process and weld surface image information are input into a performance prediction and evaluation module. The module is used for obtaining a prediction evaluation result of the strength of the welding joint and judging whether the current welding joint meets the design strength requirement or not, so that the post-welding nondestructive testing is avoided.
In order to achieve the above object, the technical scheme of the present invention is as follows:
the utility model provides an on-line monitoring system for stirring friction welding process, includes vision module, temperature measurement module, feedback execution module, performance prediction and evaluation module, vision module is arranged in image information gathers and transmits the image information who gathers to feedback execution module, temperature measurement module is arranged in real-time temperature gathers and transmits real-time temperature to feedback execution module, feedback execution module is arranged in material welding and technological parameter adjustment and all information integration transmission that acquire to performance prediction and evaluation module, and performance prediction and evaluation module analysis obtains the information that the welding joint intensity predicts the evaluation result.
The visual module comprises a CCD industrial camera and a spherical clamp, the CCD industrial camera is arranged below an upper pressing plate of a workbench of the friction stir welding machine through the spherical clamp, a first dial and a second dial are coaxially arranged at the connection position of the spherical clamp and the CCD industrial camera, the second dial is close to one side of the CCD industrial camera, the spherical clamp comprises a ball head, a guide rod and a bolt, the guide rod penetrates through the center of the ball head, the ball head is fixed with the guide rod through the bolt, the number of the CCD industrial cameras is two, and the CCD industrial cameras are arranged below the right side of the upper pressing plate of the workbench of the friction stir welding machine.
The temperature measuring module comprises an optical fiber infrared thermometer, a universal bamboo joint pipe, an electric air pump, a sliding rail device and a dual-wavelength infrared temperature measuring model arranged in a computer, wherein the sliding rail device is arranged below an upper pressing plate of a friction stir welding machine, an angle dial is carved on the sliding rail device, two sliding blocks are arranged in the sliding rail through bolts, the two optical fiber infrared thermometers respectively penetrate through the universal bamboo joint pipe and are arranged below the sliding blocks, the sliding rail device adopts a U-shaped guide rail design and is connected with the upper pressing plate of the welding machine through bolts, the electric air pump is placed on one side of the friction stir welding machine, one end of a soft PVC (polyvinyl chloride) guide pipe is connected with an air outlet of the electric air pump, the other end of the soft PVC guide pipe is arranged beside the optical fiber infrared thermometers, and the optical fiber infrared thermometers input the measured radiation intensity of two wavelengths into the dual-wavelength infrared temperature measuring model, so that the measured temperature is obtained.
The dual-wavelength infrared temperature measurement model is a formula model obtained by minimizing a cost function through a calculus method and solving model parameters, and the formula is as follows:
T=α 3 ×(r ΔDR (T)/C f r ε (T)) 3 +α 2 ×(r ΔDR (T)/C f r ε (T)) 2 +α 1 ×(r ΔDR (T)/C f r ε (T))+α 0
wherein r is ΔDR (T) is the ratio of the average radiation intensity of two wave bands, C f To make the correction factor constant, r ε (T) is the average emissivity ratio of two wave bands, alpha 3 、α 2 、α 1 、α 0 Parameters are set for the model.
The feedback execution module comprises a friction stir welding machine, a friction stir welding machine workbench, a pressure sensor, a process auxiliary computer, a parameter adjusting mechanism and a liquid crystal display, wherein the temperature measuring module transmits the measured real-time temperature to the process auxiliary computer, the process auxiliary computer comprises a temperature intelligent regulation decision model, the real-time temperature is compared with the peak temperature and the lowest temperature of a temperature circulation curve in a process auxiliary computer database, the temperature circulation curve is the temperature fluctuation range of a welding joint when an ideal welding joint surface is obtained, the peak temperature and the lowest temperature are the boundaries of the temperature circulation curve, and if the real-time temperature is in the peak temperature and the lowest temperature range, welding is continued; if the real-time temperature is not in the peak temperature and the lowest temperature range, calculating a temperature difference value from the real-time temperature to the peak temperature or the value close to the lowest temperature, transmitting the obtained temperature difference value to a temperature intelligent regulation decision model, thereby obtaining a pressing quantity adjustment quantity, wherein the parameter adjustment executing mechanism comprises a servo fine adjustment motor and a sliding vertical guide rail, the sliding vertical guide rail is arranged above a friction stir welding machine workbench, one side of a pressing plate on the friction stir welding machine workbench is arranged in the sliding vertical guide rail, the pressing plate on the friction stir welding machine workbench is connected with the sliding vertical guide rail, the servo fine adjustment motor is used for controlling the pressing plate on the friction stir welding machine workbench to move up and down in the sliding vertical guide rail, the parameter adjustment executing mechanism is electrically connected with the friction stir welding machine and the process auxiliary computer, and the process auxiliary computer sends instructions to the parameter adjustment executing mechanism according to the pressing quantity adjustment quantity: when the real-time temperature of the welding area is in the peak temperature and the lowest temperature range, the current shaft shoulder pressing quantity parameter is unchanged; if the temperature difference value of the welding area is a positive value, inputting the temperature difference value into a temperature intelligent regulation decision model to obtain an adjustment quantity for reducing the downward pressure quantity of the shaft shoulder; when the temperature difference value of the welding area is negative, the temperature difference value is input into a temperature intelligent regulation decision model to obtain an adjustment quantity for increasing the pressing quantity of the shaft shoulder, a pressure sensor is arranged at the joint of a main shaft of the welding machine and a stirring head clamp to measure stirring head pressure information, the stirring head pressure information is transmitted to a process auxiliary computer through a pressure data signal wire, a liquid crystal display is arranged on the friction stir welding machine and is electrically connected with the process auxiliary computer, and if the pressure value exceeds the theoretical heat input maximum critical pressure in the process auxiliary computer, the liquid crystal display displays an alarm signal and is used for displaying the current axial pressure, the real-time temperature and the pressing adjustment quantity information of the welding shaft shoulder.
The intelligent temperature regulation decision model adopts a neural network prediction model, the neural network prediction model comprises BP neural network structures of two hidden layers, the parameters of an input layer comprise the rotating speed, the welding speed, the pressing-down amount and the temperature difference value of a welding area of a friction stir welding machine, and the number of neuron nodes of the input layer of the neural network prediction model is 4; the output layer parameter of the neural network prediction model is the adjustment quantity of the pressing quantity, and the number of the neuron nodes of the output layer is 1; the selected activation function is the tanh function and the loss function is the cross entropy loss function.
The performance prediction and assessment module adopts a multi-mode fusion learning method, the multi-mode fusion learning method relates to integrating information from different modes, wherein for a welding joint surface texture image acquired by the vision module, a convolutional neural network is adopted to perform feature extraction so as to capture texture information of the image, and temperature information acquired by the temperature measurement module, welding process parameters and image feature information form an input vector of a fully-connected neural network by using a multi-mode feature fusion method based on splicing fusion; the output layer adopts a sigmoid activation function to limit the output between 0 and 1; the random gradient descent algorithm is adopted to optimize the loss function, the GA optimization algorithm is used to optimize the initial weight and the threshold of the convolutional neural network, the classification accuracy is used as the fitness function, the optimized initial weight and threshold of the convolutional neural network are obtained through selection, crossing and compiling operations, a large number of welding tests are conducted for constructing a welding seam strength evaluation model dataset, and different rotating speeds, welding speeds and pressing amounts are covered.
The friction stir welding process on-line monitoring and parameter control method for the friction stir welding process on-line monitoring system comprises the following steps:
step 1: the welding process on-line monitoring system is assembled, a workpiece is placed on a welding machine workbench, a vision module is adjusted to ensure that a CCD industrial camera can acquire welding seam image information under the condition of no shielding, the position of an optical fiber infrared thermometer is adjusted to ensure the accuracy of a distance measurement target, the vision module is used for acquiring the welding seam image information, the temperature module is used for acquiring real-time temperature information, the pressure sensor is used for acquiring stirring head pressure information, welding equipment is used for acquiring welding process information, and the acquired welding seam image information, the real-time temperature information, the stirring head pressure information and the welding process information are transmitted to a process auxiliary computer.
Step 2: setting resolution, frame rate and exposure time in camera software in a computer, performing system debugging to ensure that images captured by a CCD industrial camera meet expectations, checking the quality of the captured images, testing the triggering and synchronizing functions of the CCD industrial camera to ensure reliability in an automatic control process, setting an optical fiber infrared thermometer, including adjusting a temperature display unit, utilizing aiming laser on the optical fiber infrared thermometer to ensure alignment of a temperature measuring target, realizing an automatic triggering mechanism of temperature measurement, and selecting welding process parameters according to the type and thickness of aluminum alloy plates, parameters of a welding tool and process requirements to perform friction stir welding.
Step 3: the temperature measurement module transmits the real-time temperature to the process auxiliary computer, compares the real-time temperature with the peak temperature and the lowest temperature of the temperature cycle curve in the process auxiliary computer database, and if the real-time temperature is in the peak temperature and the lowest temperature range, continues welding; if the measured temperature is not in the allowable range, subtracting the peak temperature from the measured temperature to obtain a temperature difference value, if the measured temperature is less than the minimum temperature, subtracting the minimum temperature from the measured temperature to obtain a temperature difference value, and transmitting the obtained temperature difference value to a temperature intelligent regulation decision model so as to obtain a pressing amount adjustment quantity, wherein the welding process auxiliary computer sends an instruction to the parameter adjustment executing mechanism according to the pressing amount adjustment quantity, and when the temperature difference value is in the allowable temperature range, the current shaft shoulder pressing amount parameter is unchanged; if the temperature difference is a positive value, inputting the temperature difference into a temperature intelligent regulation decision model to obtain an adjustment quantity for reducing the downward pressure quantity of the shaft shoulder; when the temperature difference is negative, the temperature difference is input into a temperature intelligent regulation decision model to obtain the regulating variable for increasing the downward pressure of the shaft shoulder.
Step 4: the parameter adjustment executing mechanism receives an adjustment instruction of the welding process auxiliary computer, corrects the process parameters input by a numerical control system of the welding machine in the friction stir welding machine, controls the upper pressing plate of the workbench of the friction stir welding machine to move in the vertical sliding guide rail along the direction of the main shaft through the servo fine adjustment motor so as to control the change of the pressing quantity parameter, and forms circulation control to achieve the aim of continuous steady-state welding;
step 5: inputting the acquired real-time temperature of the welding joint, the technological parameters in the welding process and the welding seam surface image information processed by camera software into a performance prediction and evaluation module to obtain a welding joint strength prediction evaluation result, and if the output result is marked as 1, indicating that the welding joint strength prediction evaluation result meets the strength design standard, and carrying out acceptance of a subsequent structure; if the output result is 0, the strength is not qualified.
The invention has the beneficial effects that:
(1) The comparison and control of the real-time temperature data monitoring of the welding seam and the peak temperature of the temperature field ensure that the temperature fluctuation along the welding seam direction is in a controllable range, and the strength stability of the welding structure is greatly enhanced;
(2) Based on a dual-wavelength temperature detection method, the temperature of the aluminum alloy friction stir welding with the variable emissivity material under a non-contact condition can be accurately measured, and compared with a contact type temperature measurement method, the temperature measurement efficiency is improved; based on the measured temperature fluctuation result, a temperature intelligent regulation decision model is introduced, so that accurate regulation and control of welding parameters based on temperature stability in the welding process can be realized.
(3) Based on the strong image processing capability of the convolutional neural network, the multi-mode fusion learning method is combined with the prior knowledge of the technological process to construct a welding joint strength prediction evaluation model, so that the online accurate prediction of the welding joint strength is realized, and the nondestructive detection after welding is avoided.
(4) The image information acquisition, the temperature measurement and the process parameter recording of the whole welding process are realized through the cooperative work of the vision module, the temperature measurement module and the welding process auxiliary computer, and the data support is provided for the research and development of the intelligent friction stir welding technology.
Drawings
FIG. 1 is a schematic diagram of the overall structure of an online monitoring system for a stir welding process;
FIG. 2 is a bottom view of a friction stir welding machine table top platen provided by the present invention;
FIG. 3 is a logic flow diagram of an on-line monitoring and parameter control method for a stir welding process provided by the invention;
FIG. 4 is a flow chart of a model for decision-making adjustment of the amount of depression provided by the present invention;
FIG. 5 is a flow chart of a performance prediction and assessment model provided by the present invention;
FIG. 6 is a flow chart of a performance prediction and assessment model training provided by the present invention.
Reference numerals in the drawings of the specification include:
the device comprises a 01-friction stir welding machine, a 08-main shaft, a 09-parameter adjustment executing mechanism, a 10-friction stir welding machine workbench upper pressing plate, an 11-sliding vertical guide rail, a 14-liquid crystal display, a 15-stirring head, a 16-welding process auxiliary computer, a 17-workpiece, a 23-guide rod, a 24-bolt, a 26-spherical clamp, a 28-universal bamboo joint pipe, a 31-electric air pump, a 32-optical fiber infrared thermometer, a 34-PVC conduit, a 36-CCD industrial camera, a 38-pressure sensor, a 41-dial I, a 42-dial II, a 44-slide block, a 45-bolt, a 46-slide rail device and a 48-angle dial.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention.
As shown in fig. 1 to 6, the online monitoring system for the stirring and wiping welding process comprises a vision module, a temperature measuring module, a feedback execution module and a performance prediction and evaluation module, wherein the vision module is used for collecting image information and transmitting the collected image information to the feedback execution module, the temperature measuring module is used for collecting real-time temperature and transmitting the real-time temperature to the feedback execution module, the feedback execution module is used for material welding and process parameter adjustment, and integrating all the obtained information and transmitting the obtained information to the performance prediction and evaluation module, and the performance prediction and evaluation module analyzes the obtained information to obtain a welding joint strength prediction evaluation result.
The visual module comprises a CCD industrial camera 36 and a spherical clamp 26, wherein the CCD industrial camera 36 is arranged below the upper platen 10 of the friction stir welding machine workbench through the spherical clamp 26, a first dial 41 and a second dial 42 are coaxially arranged at the connection position of the spherical clamp 26 and the CCD industrial camera 36, the second dial 42 is close to one side of the CCD industrial camera 36, the spherical clamp comprises a ball head, a guide rod and a bolt, the guide rod penetrates through the center of the ball head, the ball head is fixed with the guide rod through the bolt, in order to prevent shielding of welding images and information loss, two CCD industrial cameras 36 are adopted for image information acquisition, and the CCD industrial camera 36 is arranged below the right side of the upper platen 10 of the friction stir welding machine workbench. The ball head is fastened with the guide rod 23 through the bolt 24 to adjust the vertical height and the plane angle of the camera, the second dial 42 at the joint of the CCD industrial camera 36 and the ball head is used for fine adjustment of the camera angle, and the CCD industrial camera 36 can acquire the image information of the welding seam under the condition of no shielding through adjustment of the guide rod 23 and the first dial 41.
The temperature measuring module comprises an optical fiber infrared thermometer 32, a universal bamboo joint pipe 28, an electric air pump 31, a sliding rail device 46 and a dual-wavelength infrared temperature measuring model arranged in a computer, wherein the sliding rail device 46 is arranged below a stirring friction welder workbench 10, an angle dial 48 is carved on the sliding rail device 46, two sliding blocks 44 are arranged in the sliding rail device 46 through bolts, the two optical fiber infrared thermometers 32 respectively penetrate through the universal bamboo joint pipe 28 and are arranged below the sliding blocks 44, the sliding rail device 46 adopts a U-shaped guide rail design and is connected with the stirring friction welder workbench 10 through bolts, the angle dial 48 on the sliding rail device 46 is adjusted to ensure that laser of the optical fiber infrared thermometers is aligned with the advancing side or the retreating side of a stirring head 15, the electric air pump 31 is arranged at the position 5mm away from the outer side of a shaft shoulder, one end of the stirring friction welder workbench, one end of a soft PVC conduit 34 is connected with an air outlet of the electric air pump 31, the other end of the soft PVC conduit 34 is arranged beside the optical fiber infrared thermometers 32, the soft PVC conduit 34 guides compressed air to the infrared thermometers so as to clear dust, the optical fiber infrared thermometers are accurately input into the dual-wavelength infrared radiation measuring model of the optical fiber infrared thermometers 32, and the dual-wavelength infrared radiation measuring module is obtained.
The dual-wavelength infrared temperature measurement model considers that the emissivity of the aluminum alloy changes along with the temperature change, adopts a dual-wavelength temperature measurement method when the temperature measurement of a welded joint is carried out, and combines the method with the selection of the optimal welding peak temperature TAccording to wien's law of displacementb is a wien displacement constant, and the peak wavelength lambda is selected 1 、λ 2 In this process, to ensure that the two selected peak wavelengths are similar and to avoid the infrared absorption bands of water vapor and carbon dioxide at the same time, to improve the accuracy and reliability of the measurement, the method uses two infrared bandpass filters with center transmission wavelengths of λ, respectively 1 、λ 2 FWHM bandwidths are μ;
where DR (T) is the measured target radiation intensity, ε (T) is the emissivity of the aluminum alloy as a function of temperature, λ is the center projection wavelength, τ λ Spectral transmittance of the infrared band-pass filter, C 1 、C 2 For the first and second radiation constants, F is the detector offset,
wherein DeltaDR (T) is the differential radiation intensity under two different temperature measurement targets, epsilon (T) is the emissivity of the aluminum alloy related to temperature, lambda is the central projection wavelength, tau λ Spectral transmittance of the infrared band-pass filter, C 1 、C 2 Is the first and second radiation constants, T ambient In order to be at the temperature of the environment,
wherein D (T) is the measured target temperature, r ΔDR (T) is the ratio of the average radiation intensity of two wave bands, C f To make the correction factor constant, r ε (T) is the average emissivity ratio of two wave bands, lambda 1 、λ 2 Respectively two infrared band-pass filters with central transmission wavelength (mu) of FWHMBandwidth, τ λ1 、τ λ2 Spectral transmittance of two infrared band-pass filters, C 1 、C 2 Is the first and second radiation constants, T ambient Is ambient temperature.
The optical fiber infrared thermometer uses the formula (1) to calculate the difference between the radiation intensity measured in the welding process and the radiation intensity measured at the ambient temperature, thereby obtaining the formula (2). By the process, the influence of the drift amount of the detector is corrected, and the accuracy of temperature measurement is ensured. And then, calculating the ratio of the two radiation intensities subjected to the correction of the central transmission wavelength to eliminate the influence of non-wavelength factors, thereby obtaining a dual-wavelength temperature measurement formula (3).
It can be seen from the thermometry equation (3) that the temperature is only related to the radiation intensities of two adjacent wavelengths. The right side of the equation can measure the corresponding radiation intensity through the light infrared thermometer. In order to obtain the numerical solution of the temperature measurement equation, the aluminum alloy plate is placed in a resistance heating device for heating and temperature measurement, the temperature range is 100-500 ℃, and the temperature interval is T step =2 to 20K. And measuring the temperature of the aluminum alloy plate by using a thermocouple, and simultaneously, respectively measuring the radiation intensity of the plate by using two optical fiber infrared temperature measuring devices to obtain a series of plate temperatures and corresponding radiation intensity data. Then, a polynomial numerical model between the radiation intensity and the temperature of the plate is established by using a least square method, and a cost function is minimized by a calculus method to solve model parameters, so that a final infrared temperature measurement model T=alpha is obtained 3 ×(r ΔDR (T)/C f r ε (T)) 3 +α 2 ×(r ΔDR (T)/C f r ε (T)) 2 +α 1 ×(r ΔDR (T)/C f r ε (T))+α 0 Wherein r is ΔDR (T) is the ratio of the average radiation intensity of two wave bands, C f To make the correction factor constant, r ε (T) is the average emissivity ratio of two wave bands, alpha 3 、α 2 、α 1 、α 0 Parameters are set for the model. Alpha 3 、α 2 、α 1 、α 0 Obtaining a series of temperature and radiation by temperature measurement as parameters of a polynomial numerical modelAnd finally obtaining the parameter value of the numerical model according to the intensity data and a least square method calculation method, and inputting the radiation intensity of the unknown temperature into the polynomial numerical model so as to calculate the unknown temperature value. In the welding process, the measured radiation intensities of two wavelengths are input into an infrared temperature measurement model, so that the accurate measurement of the temperature of the welding joint is realized.
The feedback execution modules include friction stir welding machine 01, pressure sensor 38, friction stir welding machine table, process assist computer 16, and liquid crystal display 14. The temperature measurement module is used for transmitting the real-time temperature of the stirring head 15, which is 5mm away from the shaft shoulder, to the process auxiliary computer 16, wherein the process auxiliary computer 16 comprises a temperature intelligent regulation decision model, the real-time temperature is compared with the peak temperature and the lowest temperature of a temperature circulation curve in a process auxiliary computer database, the temperature circulation curve is the temperature fluctuation range of a welding joint when an ideal welding joint surface is obtained, the peak temperature and the lowest temperature are the boundaries of the temperature circulation curve, and if the real-time temperature is in the peak temperature and the lowest temperature range, the welding is continued; if the real-time temperature is not in the peak temperature and the lowest temperature range, calculating a temperature difference value between the real-time temperature and a value close to the peak temperature or the lowest temperature, and transmitting the temperature difference value to a temperature intelligent regulation decision model, so that the pressing quantity regulating quantity is obtained. The parameter adjustment executing mechanism 09 comprises a servo fine adjustment motor and a sliding vertical guide rail 11, the sliding vertical guide rail 11 is arranged above a friction stir welding machine workbench, one side of a pressing plate 10 on the friction stir welding machine workbench is arranged in the sliding vertical guide rail 11, the pressing plate 10 on the friction stir welding machine workbench is connected with the sliding vertical guide rail 11, the pressing plate on the friction stir welding machine workbench is controlled to move up and down in the sliding vertical guide rail 11 by the servo fine adjustment motor, the parameter adjustment executing mechanism 09 is electrically connected with the friction stir welding machine 01 and a process auxiliary computer 16, and the process auxiliary computer 16 sends instructions to the parameter adjustment executing mechanism according to the pressing amount adjustment quantity: when the temperature difference value of the welding area is within the allowable temperature range, the current shaft shoulder pressing quantity parameter is unchanged; if the temperature difference value of the welding area is a positive value, inputting the temperature difference value into a temperature intelligent regulation decision model to obtain an adjustment quantity for reducing the downward pressure quantity of the shaft shoulder; when the temperature difference value of the welding area is a negative value, inputting the temperature difference value into a temperature intelligent regulation decision model to obtain the regulating variable for increasing the downward pressure of the shaft shoulder. The pressure sensor 38 is installed at the position where the welding machine main shaft 08 is connected with the clamp of the stirring head 15, and is connected with the process auxiliary computer 16 through a pressure data signal wire to measure the pressure information of the stirring head, and is connected with the process auxiliary computer 16 through a pressure data signal wire to transmit the pressure information of the stirring head to the process auxiliary computer 16. A liquid crystal display 14 is mounted on the friction stir welding machine 01 and is electrically connected to the process aid computer 16, and if the pressure value exceeds a critical threshold, the liquid crystal display 14 will display an alarm signal. The liquid crystal display 14 is used for displaying the current axial pressure of the stirring head, real-time temperature, downward pressure adjustment quantity of the welding shaft shoulder and the like.
The temperature intelligent regulation decision model adopts a BP neural network structure with a neural network prediction model comprising two hidden layers, and the parameters of an input layer comprise the rotating speed, the welding speed and the pressing quantity of a friction stir welding machine and the temperature difference value of a welding area, wherein the number of neuron nodes of the input layer is 4; the output layer parameter of the model is the adjustment quantity of the pressing quantity, and the number of the neuron nodes of the output layer is 1; the selected activation function is the tanh function and the loss function is the cross entropy loss function. In order to construct a temperature intelligent regulation decision model data set, a large number of welding experiments are carried out on the aluminum alloy by using different welding process parameters, and the difference value between the theoretical pressing-down amount and the artificial experience pressing-down amount is recorded as a label of a training sample in the welding process.
The performance prediction and assessment module adopts a multi-mode fusion learning method to integrate information from different modes, and aims to integrate information from different modes so as to solve the problem of welding joint strength assessment. And the characteristic extraction is carried out on the welding joint surface texture information image acquired by the vision module by adopting a convolutional neural network so as to capture the texture information of the image. The temperature information, welding process parameters and image characteristic information acquired by the temperature measuring module are based on a multi-mode characteristic fusion method of splicing and fusion to form an input vector of the fully-connected neural network. The output layer uses a sigmoid activation function to limit the output to between 0 and 1. And a random gradient descent algorithm is adopted to optimize a loss function, so that intelligent evaluation of the strength of the welded joint is realized. In order to construct a weld strength evaluation model dataset, a large number of welding tests are performed, covering different rotational speeds, welding speeds and pressing amounts. And acquiring welding line pictures, welding joint temperatures and tensile strength of the test samples under different process parameters in an experiment. Samples meeting the corresponding strength requirements are labeled 1, and samples not meeting the requirements are labeled 0.
The friction stir welding process on-line monitoring and parameter control method for the friction stir welding process on-line monitoring system comprises the following steps:
step 1: the on-line monitoring system for the assembly stirring friction welding process is characterized in that a workpiece 17 is placed on a welding machine workbench, a vision module is adjusted, the fact that a CCD industrial camera 36 can acquire welding seam image information without shielding is ensured, the position of an optical fiber infrared thermometer 32 is adjusted to ensure the accuracy of a distance measurement target, the vision module acquires welding seam image information, the temperature module acquires real-time temperature information, the pressure sensor acquires stirring head pressure information, the welding equipment acquires welding process information, and the acquired welding seam image information, the real-time temperature information, the stirring head pressure information and the welding process information are transmitted to a process auxiliary computer.
Step 2: parameters such as resolution, frame rate, exposure time, etc. are set in camera software in the computer, system debugging is performed to ensure that the image captured by the CCD industrial camera 36 meets expectations and to check the image quality. The triggering and synchronization functions of the CCD industrial camera 36 are tested to ensure reliability in the automated control process. The optical fiber infrared thermometer is set, including adjustment of a temperature display unit, and aiming laser on the optical fiber infrared thermometer 32 is utilized to ensure alignment of a temperature measurement target, so that an automatic triggering mechanism for temperature measurement is realized. And selecting welding process parameters according to the types and thicknesses of the aluminum alloy plates, parameters of a welding tool and process requirements so as to perform friction stir welding.
Step 3: the temperature measurement module transmits the real-time temperature to the process auxiliary computer 16, compares the real-time temperature with the peak temperature and the lowest temperature of a temperature cycle curve in a database of the process auxiliary computer 16, and if the real-time temperature is within the peak temperature and the lowest temperature range, continues welding; if the measured temperature is not in the allowable range, subtracting the peak temperature from the measured temperature to obtain a temperature difference value, if the measured temperature is less than the minimum temperature, subtracting the minimum temperature from the measured temperature to obtain a temperature difference value, transmitting the obtained temperature difference value to a temperature intelligent regulation decision model so as to obtain a pressing amount adjustment amount, and sending an instruction to a parameter adjustment executing mechanism 09 by a welding process auxiliary computer according to the pressing amount adjustment amount, wherein when the temperature difference value is in the allowable temperature range, the current shaft shoulder pressing amount parameter is unchanged; if the temperature difference is a positive value, inputting the temperature difference into a temperature intelligent regulation decision model to obtain an adjustment quantity for reducing the downward pressure quantity of the shaft shoulder; when the temperature difference is negative, the temperature difference is input into a temperature intelligent regulation decision model to obtain the regulating variable for increasing the downward pressure of the shaft shoulder.
Step 4: the parameter adjustment executing mechanism 09 receives an adjustment instruction of the welding process auxiliary computer 16, corrects the process parameters input by a numerical control system of the welding machine in the friction stir welding machine 01, and controls the upper pressing plate of the workbench of the friction stir welding machine to move in the vertical sliding guide rail 11 along the direction of the main shaft 08 by the servo fine adjustment motor so as to control the change of the pressing quantity parameter, thereby forming the circulation control so as to achieve the aim of continuous steady-state welding.
Step 5: inputting the acquired temperature data, the technological parameters in the welding process and the welding seam surface image information into a performance prediction and evaluation module to obtain a welding joint strength prediction evaluation result, and if the output result is marked as 1, indicating that the strength design standard is met, and carrying out acceptance of a subsequent structure; if the output result is 0, the strength is not qualified. This provides data support for subsequent structural inspection, as well as a basis for whether repair welding is required.
Claims (8)
1. The online monitoring system for the friction stir welding process is characterized by comprising a vision module, a temperature measuring module, a feedback execution module and a performance prediction and assessment module, wherein the vision module is used for collecting image information and transmitting the collected image information to the feedback execution module, the temperature measuring module is used for collecting real-time temperature and transmitting the real-time temperature to the feedback execution module, the feedback execution module is used for material welding and process parameter adjustment and integrating all acquired information and transmitting all acquired information to the performance prediction and assessment module, and the performance prediction and assessment module analyzes the acquired information to acquire a welding joint strength prediction assessment result.
2. The online monitoring system for the friction stir welding process according to claim 1, wherein the vision module comprises a CCD industrial camera and a spherical clamp, the CCD industrial camera is arranged below an upper pressing plate of a workbench of the friction stir welding machine through the spherical clamp, a first dial and a second dial are coaxially arranged at the connecting position of the spherical clamp and the CCD industrial camera, the second dial is close to one side of the CCD industrial camera, the spherical clamp comprises a ball head, a guide rod and a bolt, the guide rod penetrates through the center of the ball head, the ball head and the guide rod are fixed through the bolt, the number of the CCD industrial cameras is two, and the CCD industrial camera is arranged below the right side of the upper pressing plate of the workbench of the friction stir welding machine.
3. The online monitoring system for the friction stir welding process according to claim 2, wherein the temperature measuring module comprises an optical fiber infrared thermometer, a universal bamboo joint pipe, an electric air pump, a sliding rail device and a dual-wavelength infrared temperature measuring model arranged in a computer, wherein the sliding rail device is arranged below an upper pressing plate of a workbench of the friction stir welding machine, an angle dial is carved on the sliding rail device, two sliding blocks are arranged in the sliding rail through bolts, the two optical fiber infrared thermometers respectively penetrate through the universal bamboo joint pipe to be arranged below the sliding blocks, the sliding rail device adopts a U-shaped guide rail design and is connected with the upper pressing plate of the workbench of the welding machine through bolts, the electric air pump is arranged on one side of the workbench of the friction stir welding machine, one end of a soft PVC guide pipe is connected with an air outlet of the electric air pump, the other end of the soft PVC guide pipe is arranged beside the optical fiber infrared thermometer, and the optical fiber infrared thermometers input the measured radiation intensities of two wavelengths into the dual-wavelength infrared temperature measuring model, so that the measured temperature is obtained.
4. The online monitoring system for a friction stir welding process according to claim 3, wherein the dual-wavelength infrared temperature measurement model is a formula model obtained by minimizing a cost function through a calculus method and solving model parameters, and the formula is as follows:
T=α 3 ×(r ΔDR (T)/C f r ε (T)) 3 +α 2 ×(r ΔDR (T)/C f r ε (T)) 2 +α 1 ×(r ΔDR (T)/C f r ε (T))+α 0
wherein r is ΔDR (T) is the ratio of the average radiation intensity of two wave bands, C f To make the correction factor constant, r ε (T) is the average emissivity ratio of two wave bands, alpha 3 、α 2 、α 1 、α 0 Parameters are set for the model.
5. The online monitoring system for a friction stir welding process according to claim 4, wherein the feedback execution module comprises a friction stir welding machine, a friction stir welding machine workbench, a pressure sensor, a process auxiliary computer, a parameter adjusting mechanism and a liquid crystal display, the temperature measurement module transmits the measured real-time temperature to the process auxiliary computer, the process auxiliary computer comprises a temperature intelligent regulation decision model, the real-time temperature is compared with the peak temperature and the lowest temperature of a temperature cycle curve in a process auxiliary computer database, the temperature cycle curve is the temperature fluctuation range of a welding joint when an ideal welding line surface is obtained, the peak temperature and the lowest temperature are the boundaries of the temperature cycle curve, and if the real-time temperature is within the peak temperature and the lowest temperature range, welding is continued; if the real-time temperature is not in the peak temperature and the lowest temperature range, calculating a temperature difference value from the real-time temperature to the peak temperature or the value close to the lowest temperature, transmitting the obtained temperature difference value to a temperature intelligent regulation decision model, thereby obtaining a pressing quantity adjustment quantity, wherein the parameter adjustment executing mechanism comprises a servo fine adjustment motor and a sliding vertical guide rail, the sliding vertical guide rail is arranged above a friction stir welding machine workbench, one side of a pressing plate on the friction stir welding machine workbench is arranged in the sliding vertical guide rail, the pressing plate on the friction stir welding machine workbench is connected with the sliding vertical guide rail, the servo fine adjustment motor is used for controlling the pressing plate on the friction stir welding machine workbench to move up and down in the sliding vertical guide rail, the parameter adjustment executing mechanism is electrically connected with the friction stir welding machine and the process auxiliary computer, and the process auxiliary computer sends instructions to the parameter adjustment executing mechanism according to the pressing quantity adjustment quantity: when the real-time temperature of the welding area is in the peak temperature and the lowest temperature range, the current shaft shoulder pressing quantity parameter is unchanged; if the temperature difference value of the welding area is a positive value, inputting the temperature difference value into a temperature intelligent regulation decision model to obtain an adjustment quantity for reducing the downward pressure quantity of the shaft shoulder; when the temperature difference value of the welding area is negative, the temperature difference value is input into a temperature intelligent regulation decision model to obtain an adjustment quantity for increasing the pressing quantity of the shaft shoulder, a pressure sensor is arranged at the joint of a main shaft of the welding machine and a stirring head clamp to measure stirring head pressure information, the stirring head pressure information is transmitted to a process auxiliary computer through a pressure data signal wire, a liquid crystal display is arranged on the friction stir welding machine and is electrically connected with the process auxiliary computer, and if the pressure value exceeds the theoretical heat input maximum critical pressure in the process auxiliary computer, the liquid crystal display displays an alarm signal and is used for displaying the current axial pressure, the real-time temperature and the pressing adjustment quantity information of the welding shaft shoulder.
6. The online monitoring system for a friction stir welding process according to claim 5, wherein the temperature intelligent regulation decision model adopts a neural network prediction model, the neural network prediction model comprises a BP neural network structure of two hidden layers, input layer parameters of the BP neural network structure comprise the rotating speed, the welding speed, the pressing quantity and the welding area temperature difference value of a friction stir welding machine, and the number of neuron nodes of the input layer of the neural network prediction model is 4; the output layer parameter of the neural network prediction model is the adjustment quantity of the pressing quantity, and the number of the neuron nodes of the output layer is 1; the selected activation function is the tanh function and the loss function is the cross entropy loss function.
7. The online monitoring system for a friction stir welding process according to claim 6, wherein the performance prediction and assessment module adopts a multi-modal fusion learning method, the multi-modal fusion learning method involves integrating information from different modalities, wherein for a welding joint surface texture image acquired by a vision module, a convolutional neural network is adopted to perform feature extraction so as to capture texture information of the image, and temperature information acquired by a temperature measurement module, welding process technological parameters and image feature information form an input vector of a fully connected neural network by using a multi-modal feature fusion method based on splicing fusion; the output layer adopts a sigmoid activation function to limit the output between 0 and 1; the random gradient descent algorithm is adopted to optimize the loss function, the GA optimization algorithm is used to optimize the initial weight and the threshold of the convolutional neural network, the classification accuracy is used as the fitness function, the optimized initial weight and threshold of the convolutional neural network are obtained through selection, crossing and compiling operations, a large number of welding tests are conducted for constructing a welding seam strength evaluation model dataset, and different rotating speeds, welding speeds and pressing amounts are covered.
8. A friction stir welding process on-line monitoring and parameter control method for a friction stir welding process on-line monitoring system as recited in claim 7, comprising the steps of:
step 1: the method comprises the steps of assembling an online monitoring system for a stirring and wiping welding process, placing a workpiece on a welding machine workbench, adjusting a vision module to ensure that a CCD industrial camera can acquire welding seam image information under the condition of no shielding, adjusting the position of an optical fiber infrared thermometer to ensure the accuracy of a distance measurement target, acquiring the welding seam image information by the vision module, acquiring real-time temperature information by the temperature measuring module, acquiring stirring head pressure information by a pressure sensor, acquiring welding process information by welding equipment, and transmitting the acquired welding seam image information, real-time temperature information, stirring head pressure information and welding process information to a process auxiliary computer;
step 2: setting resolution, frame rate and exposure time in camera software in a computer, performing system debugging to ensure that images captured by a CCD industrial camera meet expectations, checking the quality of the captured images, testing the triggering and synchronizing functions of the CCD industrial camera to ensure reliability in an automatic control process, setting an optical fiber infrared thermometer, including adjusting a temperature display unit, utilizing aiming laser on the optical fiber infrared thermometer to ensure alignment of a temperature measuring target, realizing an automatic triggering mechanism of temperature measurement, and selecting welding process parameters according to the type and thickness of aluminum alloy plates, parameters of a welding tool and process requirements to perform friction stir welding;
step 3: the temperature measurement module transmits the real-time temperature to the process auxiliary computer, compares the real-time temperature with the peak temperature and the lowest temperature of the temperature cycle curve in the process auxiliary computer database, and if the real-time temperature is in the peak temperature and the lowest temperature range, continues welding; if the measured temperature is not in the allowable range, subtracting the peak temperature from the measured temperature to obtain a temperature difference value, if the measured temperature is less than the minimum temperature, subtracting the minimum temperature from the measured temperature to obtain a temperature difference value, and transmitting the obtained temperature difference value to a temperature intelligent regulation decision model so as to obtain a pressing amount adjustment quantity, wherein the welding process auxiliary computer sends an instruction to the parameter adjustment executing mechanism according to the pressing amount adjustment quantity, and when the temperature difference value is in the allowable temperature range, the current shaft shoulder pressing amount parameter is unchanged; if the temperature difference is a positive value, inputting the temperature difference into a temperature intelligent regulation decision model to obtain an adjustment quantity for reducing the downward pressure quantity of the shaft shoulder; when the temperature difference is negative, inputting the temperature difference into a temperature intelligent regulation decision model to obtain an adjustment quantity for increasing the downward pressure quantity of the shaft shoulder;
step 4: the parameter adjustment executing mechanism receives an adjustment instruction of the welding process auxiliary computer, corrects the process parameters input by a numerical control system of the welding machine in the friction stir welding machine, controls the upper pressing plate of the workbench of the friction stir welding machine to move in the vertical sliding guide rail along the direction of the main shaft through the servo fine adjustment motor so as to control the change of the pressing quantity parameter, and forms circulation control to achieve the aim of continuous steady-state welding;
step 5: inputting the acquired real-time temperature of the welding joint, the technological parameters in the welding process and the welding seam surface image information processed by camera software into a performance prediction and evaluation module to obtain a welding joint strength prediction evaluation result, and if the output result is marked as 1, indicating that the welding joint strength prediction evaluation result meets the strength design standard, and carrying out acceptance of a subsequent structure; if the output result is 0, the strength is not qualified.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311873226.8A CN117600701A (en) | 2023-12-29 | 2023-12-29 | Online monitoring system and control method for friction stir welding process |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311873226.8A CN117600701A (en) | 2023-12-29 | 2023-12-29 | Online monitoring system and control method for friction stir welding process |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117600701A true CN117600701A (en) | 2024-02-27 |
Family
ID=89946494
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311873226.8A Pending CN117600701A (en) | 2023-12-29 | 2023-12-29 | Online monitoring system and control method for friction stir welding process |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117600701A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117961382A (en) * | 2024-03-28 | 2024-05-03 | 江苏恒久钢构股份有限公司 | Intelligent processing control system for net rack rod pieces |
-
2023
- 2023-12-29 CN CN202311873226.8A patent/CN117600701A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117961382A (en) * | 2024-03-28 | 2024-05-03 | 江苏恒久钢构股份有限公司 | Intelligent processing control system for net rack rod pieces |
CN117961382B (en) * | 2024-03-28 | 2024-05-28 | 江苏恒久钢构股份有限公司 | Intelligent processing control system for net rack rod pieces |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN117600701A (en) | Online monitoring system and control method for friction stir welding process | |
US11373264B2 (en) | Method and means to analyze thermographic data acquired during automated fiber placement | |
CN107931802B (en) | Arc welding seam quality online detection method based on mid-infrared temperature sensing | |
US9519844B1 (en) | Infrared thermographic methods for wrinkle characterization in composite structures | |
Vasudevan et al. | Real-time monitoring of weld pool during GTAW using infra-red thermography and analysis of infra-red thermal images | |
Cai et al. | A review of in-situ monitoring and process control system in metal-based laser additive manufacturing | |
CN104977305A (en) | Welding quality analysis device based on infrared vision and analysis method thereof | |
CN103134599A (en) | Method and system for real-time monitoring of molten bath state in direct molding process of laser metal | |
CN113762240B (en) | Cladding layer geometric feature prediction method and system based on deep learning | |
CN111015006B (en) | Online monitoring method for laser-arc hybrid welding quality based on spectral information | |
Chen et al. | Research on in situ monitoring of selective laser melting: a state of the art review | |
Feng et al. | Online defect detection method and system based on similarity of the temperature field in the melt pool | |
CN116234691A (en) | Imaging system and method for determining defects in glazing | |
CN108279071A (en) | Full filed temperature field of molten pool detecting system based on two-color thermometry | |
Plotnikov et al. | Infrared-assisted acoustic emission process monitoring for additive manufacturing | |
Huang et al. | Improved convolutional neural network for laser welding defect prediction | |
Yu et al. | Monitoring of butt weld penetration based on infrared sensing and improved histograms of oriented gradients | |
Lei et al. | The development of tube-to-tubesheet welding from automation to digitization | |
WO2019184560A1 (en) | Hem rolling quality inspection method employing visual system, and system | |
Zhang et al. | An iterative algorithm to improve infrared thermographic systems’ accuracy in temperature field measurement of aluminum alloys | |
Wang et al. | A novel surface temperature sensor and random forest-based welding quality prediction model | |
KR102514450B1 (en) | Method of detecting defect in welded joint using thermal imaging camera | |
CN113588091A (en) | System and method for measuring temperature of metal molten pool in laser selected area in real time by utilizing hyperspectrum | |
CN108760641B (en) | Fusion welding process monitoring device and method based on single photon detection | |
CN220480511U (en) | Monitoring equipment for excessive height of arc additive manufacturing cladding layer |
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 |