Realizing of weld penetration control in gas tungsten arc welding requires establishment of a model describing the relationship between the front-side geometrical parameters of weld pool and the back-side weld width w...Realizing of weld penetration control in gas tungsten arc welding requires establishment of a model describing the relationship between the front-side geometrical parameters of weld pool and the back-side weld width with sufficient accuracy. A neural network model is developed to attain this aim. Welding experiments are conducted to obtain the training data set （including 973 groups of geometrical parameters of the weld pool and back-side weld width） and the verifying data set （108 groups）. Two data sets are used for training and verifying the neural network, respectively. The testing results show that the model has sufficient accuracy and can meet the requirements of weld penetration control.展开更多
This paper analyses the performance request of arc welding power source used in intelligent control of weld pool shape in pulsed GTAW, and develops a sample power source. The main circuit of the power source takes the...This paper analyses the performance request of arc welding power source used in intelligent control of weld pool shape in pulsed GTAW, and develops a sample power source. The main circuit of the power source takes the structure of single ended inverter with two switches, and takes IGBTs as power switches. The working frequency of the inverter is set at 20 kHz. The control circuit takes PWM circuit as center, and uses single chip computer to complete the manage functions such as the control of working sequence, setting and changing of the welding parameters, sensing of the welding states and communication with outside computer etc. The dynamic reacting time of the whole power is 1 ms, the range of the output current is 5～250 A, the precision of the output current reaches to 1 A. The power strikes arc by contacting workpiece under 5 A, and have convenient interface with system computer. All above shows this power source is one with high performance.展开更多
Presents penetration control by weld pool resonance which occurs when the natural frequency of weld pool is equal to the frequency of sine wave current while the weld pool is excited into oscillation by superimposing ...Presents penetration control by weld pool resonance which occurs when the natural frequency of weld pool is equal to the frequency of sine wave current while the weld pool is excited into oscillation by superimposing sine wave current with definite frequency or regular frequency on DC current, and experiments carried out on detecting resonance signals during both stationary and travelling arc welding with variant frequency pulse current, and concludes with experimental results that penetration control can be realized by weld pool resonance when welding speed is lower than 80mm/min, and this control method is applicable to welding thin (0.5～3.0 mm) plates of carbon steel, low alloy steel, high strength steel and superhigh strength steel, and suitable for alternating polarity welding of stainless steel, titanium alloy steel and aluminum alloy.展开更多
Colormetric method of images by using two different wavelength images is a new measuring method for welding temperature field on the basis of ordinary colorimetric method, which depends little on the measuring distanc...Colormetric method of images by using two different wavelength images is a new measuring method for welding temperature field on the basis of ordinary colorimetric method, which depends little on the measuring distance, emissivity of body etc. In this paper the real time measuring system and measuring principle of welding temperature field are described, the whole welding temperature field is real time measured, so the temperature distribution at the welding direction and its cross section is obtained, then parameters of thermal cycle. With data from the temperature closed loop control system of the parameters of temperature field is developed and tested. Experimental results prove that it has high measurement speed (time of a field within 0.5 s ) and good dynamic response quality. Weld penetration can be controlled satisfactorily under the variation of welding condition such as welding thickness, welding speed and weldment gap etc.展开更多
To improve the penetrating ability and the welding quality of keyhole plasma arc welding, a novel penetration closed loop control system was established. In the system, welding current and plasma gas flow rate were se...To improve the penetrating ability and the welding quality of keyhole plasma arc welding, a novel penetration closed loop control system was established. In the system, welding current and plasma gas flow rate were selected as adjusting variables. The wavelet method was used to detect penetration status from welding arc voltage in real time. The control strategy of one keyhole per pulse was adapted to fulfill stable and high quality welding process. Experimental results show that the developed system can apparently increase the penetrating force of plasma arc and keyhole plasma arc welding is realized successfully in stainless steel with 10 mm in thickness. Moreover, the disturbances of gradual change and break change from 3 mm to 6 mm in thickness are come over due to the good response property of the developed system.展开更多
An intelligent system including both a neural network(NN) and a self adjusting fuzzy controller(FC) for modeling and control of the penetration depth during gas tungsten arc welding(GTAW) process is presented in this...An intelligent system including both a neural network(NN) and a self adjusting fuzzy controller(FC) for modeling and control of the penetration depth during gas tungsten arc welding(GTAW) process is presented in this paper. The discussion is mainly focused on two parts. One is the modeling of the penetration depth with NN. A visual sensor CCD is used to obtain the image of the molten pool. A neural network model is established to estimate the penetration depth from the welding current, pool width and seam gap. It is demonstrated that the proposed neural network can produce highly complex nonlinear multi variable model of the GTAW process that offer the accurate prediction of welding penetration depth. Another is the control for the penetration depth with FC.A self adjusting fuzzy controller is proposed,which used for controlling the penetration depth.The control parameters are adjusted on line automatically according to the controlling errors of penetration and the errors can be decreased sharply. The effectiveness of the proposed intelligent methods is demonstrated by the real experiments and the improved performance results are obtained.展开更多
The penetration mechanism of aluminum alloy in double-sided gas tungsten arc welding (GTAW) process was probed by means of theoretical analysis, experimentation and numerical simulation. The results show that, firstly...The penetration mechanism of aluminum alloy in double-sided gas tungsten arc welding (GTAW) process was probed by means of theoretical analysis, experimentation and numerical simulation. The results show that, firstly, the welding current goes straight through the weld zone, forms a stronger electromagnetic force field, and causes a stronger fluid flow in the weld pool. Secondly, during double-sided GTAW process, when the weld is partial penetrated, a heat-congregated zone forms between the bottoms of the two weld pools, where the temperature can increase quickly even though only a small amount of heat is input. Thirdly, the buoyancy force causes an inward flow in the bottom weld pool, which can drive the hot liquid on the surface to the bottom of the pool.展开更多
The influence of plate thickness on the penetration in GTAW was investigated and a theoretical heat flow model for a plate of finite thickness has been utilized to investigate the relationship between front and back p...The influence of plate thickness on the penetration in GTAW was investigated and a theoretical heat flow model for a plate of finite thickness has been utilized to investigate the relationship between front and back pool widths.Then,front pool width penetration control approach approach has been studied, which controls penetration under the variation of plate thickness.A penetration control system for autogenous GTA welding has been utilized which includes a coaxial weld pool imaging system and computer vision processing system to sense the front width of the GTA weld pool.Empirical results show the good performance of this penetration control approach in the presence of variations in joint plant thickness of 1 mm 0.04 inch) to 3 mm(0.125 inch)展开更多
The real-time measurement of welding temperature field by colorimetric method is described, and with the data acquired from it closed-loop control system of the parameters of temperature field is developed and tested....The real-time measurement of welding temperature field by colorimetric method is described, and with the data acquired from it closed-loop control system of the parameters of temperature field is developed and tested. Experimental results prove that it has high measurement speed (time of a field within 0.5s) and good dynamic response quality. Weld penetration can be controlled satisfactorily under unstable welding condition.展开更多
基金the Shandong Provincial Natural Science Foundation of China （No. Z2003F05 ）.
文摘Realizing of weld penetration control in gas tungsten arc welding requires establishment of a model describing the relationship between the front-side geometrical parameters of weld pool and the back-side weld width with sufficient accuracy. A neural network model is developed to attain this aim. Welding experiments are conducted to obtain the training data set （including 973 groups of geometrical parameters of the weld pool and back-side weld width） and the verifying data set （108 groups）. Two data sets are used for training and verifying the neural network, respectively. The testing results show that the model has sufficient accuracy and can meet the requirements of weld penetration control.
文摘This paper analyses the performance request of arc welding power source used in intelligent control of weld pool shape in pulsed GTAW, and develops a sample power source. The main circuit of the power source takes the structure of single ended inverter with two switches, and takes IGBTs as power switches. The working frequency of the inverter is set at 20 kHz. The control circuit takes PWM circuit as center, and uses single chip computer to complete the manage functions such as the control of working sequence, setting and changing of the welding parameters, sensing of the welding states and communication with outside computer etc. The dynamic reacting time of the whole power is 1 ms, the range of the output current is 5～250 A, the precision of the output current reaches to 1 A. The power strikes arc by contacting workpiece under 5 A, and have convenient interface with system computer. All above shows this power source is one with high performance.
文摘Presents penetration control by weld pool resonance which occurs when the natural frequency of weld pool is equal to the frequency of sine wave current while the weld pool is excited into oscillation by superimposing sine wave current with definite frequency or regular frequency on DC current, and experiments carried out on detecting resonance signals during both stationary and travelling arc welding with variant frequency pulse current, and concludes with experimental results that penetration control can be realized by weld pool resonance when welding speed is lower than 80mm/min, and this control method is applicable to welding thin (0.5～3.0 mm) plates of carbon steel, low alloy steel, high strength steel and superhigh strength steel, and suitable for alternating polarity welding of stainless steel, titanium alloy steel and aluminum alloy.
文摘Colormetric method of images by using two different wavelength images is a new measuring method for welding temperature field on the basis of ordinary colorimetric method, which depends little on the measuring distance, emissivity of body etc. In this paper the real time measuring system and measuring principle of welding temperature field are described, the whole welding temperature field is real time measured, so the temperature distribution at the welding direction and its cross section is obtained, then parameters of thermal cycle. With data from the temperature closed loop control system of the parameters of temperature field is developed and tested. Experimental results prove that it has high measurement speed (time of a field within 0.5 s ) and good dynamic response quality. Weld penetration can be controlled satisfactorily under the variation of welding condition such as welding thickness, welding speed and weldment gap etc.
文摘To improve the penetrating ability and the welding quality of keyhole plasma arc welding, a novel penetration closed loop control system was established. In the system, welding current and plasma gas flow rate were selected as adjusting variables. The wavelet method was used to detect penetration status from welding arc voltage in real time. The control strategy of one keyhole per pulse was adapted to fulfill stable and high quality welding process. Experimental results show that the developed system can apparently increase the penetrating force of plasma arc and keyhole plasma arc welding is realized successfully in stainless steel with 10 mm in thickness. Moreover, the disturbances of gradual change and break change from 3 mm to 6 mm in thickness are come over due to the good response property of the developed system.
文摘An intelligent system including both a neural network(NN) and a self adjusting fuzzy controller(FC) for modeling and control of the penetration depth during gas tungsten arc welding(GTAW) process is presented in this paper. The discussion is mainly focused on two parts. One is the modeling of the penetration depth with NN. A visual sensor CCD is used to obtain the image of the molten pool. A neural network model is established to estimate the penetration depth from the welding current, pool width and seam gap. It is demonstrated that the proposed neural network can produce highly complex nonlinear multi variable model of the GTAW process that offer the accurate prediction of welding penetration depth. Another is the control for the penetration depth with FC.A self adjusting fuzzy controller is proposed,which used for controlling the penetration depth.The control parameters are adjusted on line automatically according to the controlling errors of penetration and the errors can be decreased sharply. The effectiveness of the proposed intelligent methods is demonstrated by the real experiments and the improved performance results are obtained.
文摘The penetration mechanism of aluminum alloy in double-sided gas tungsten arc welding (GTAW) process was probed by means of theoretical analysis, experimentation and numerical simulation. The results show that, firstly, the welding current goes straight through the weld zone, forms a stronger electromagnetic force field, and causes a stronger fluid flow in the weld pool. Secondly, during double-sided GTAW process, when the weld is partial penetrated, a heat-congregated zone forms between the bottoms of the two weld pools, where the temperature can increase quickly even though only a small amount of heat is input. Thirdly, the buoyancy force causes an inward flow in the bottom weld pool, which can drive the hot liquid on the surface to the bottom of the pool.
文摘The influence of plate thickness on the penetration in GTAW was investigated and a theoretical heat flow model for a plate of finite thickness has been utilized to investigate the relationship between front and back pool widths.Then,front pool width penetration control approach approach has been studied, which controls penetration under the variation of plate thickness.A penetration control system for autogenous GTA welding has been utilized which includes a coaxial weld pool imaging system and computer vision processing system to sense the front width of the GTA weld pool.Empirical results show the good performance of this penetration control approach in the presence of variations in joint plant thickness of 1 mm 0.04 inch) to 3 mm(0.125 inch)
基金Project supported by the National Natural Science Foundation of China (Grant No. 59475064) and the Natural Science Foundation of Jiangxi Province.
文摘The real-time measurement of welding temperature field by colorimetric method is described, and with the data acquired from it closed-loop control system of the parameters of temperature field is developed and tested. Experimental results prove that it has high measurement speed (time of a field within 0.5s) and good dynamic response quality. Weld penetration can be controlled satisfactorily under unstable welding condition.
