Research on the controller of an arc welding process based on a PID neural network

A controller based on a PID neural network （PIDNN） is proposed for an arc welding power source whose output characteristic in responding to a given value is quickly and intelligently controlled in the welding process. The new method syncretizes the PID control strategy and neural network to control the welding process intelligently, so it has the merit of PID control rules and the trait of better information disposal ability of the neural network. The results of simulation show that the controller has the properties of quick response, low overshoot, quick convergence and good stable accuracy, which meet the requirements for control of the welding process.

Artificial neural networks applied to spot welding process modeling

Artificial neural networks have been studied for applicability for modeling of spot welding process. Some basic concepts relating to neural networks are explained as well as how they can be used to model welding qualitv parameters in terms of the welding process parameter. The performance of the neural networks for modeling is presented and evaluated using actual welding data. It is concluded that neural network modeling is a good means of estimating spot welding quality on-line.

Synthetically quantitative evaluation function of characteristic parameters on CO_2 arc welding process

The statistical probability and their variation regularity of the measurable characteristic parameters in the CO 2 arc welding droplet short circuiting transfer process have been studied. The statistical analysis shows that the sensitivity of each characteristic parameter with regard to the variation of the short circuiting transfer process is different. The sensitivity of 4 kinds among these characteristic parameters is more intense than that of the short circuiting transfer frequency. In order to take account of the synthetic influence of these characteristic parameters, by means of the characteristic parameters synthetic value, a quantitative evaluation function is built up to describe and evaluate the short circuiting transfer process of CO 2 arc welding in real time. The testing shows that the evaluation function can give a suitable synthetic valuation for the short circuiting transfer process with a variety of welding variables.

Approximate entropy——a new statistic to quantify arc and welding process stability in short-circuiting gas metal arc welding

Based on the phase state reconstruction of welding current in short-circuiting gas metal arc welding using carbon dioxide as shielding gas, the approximate entropy of welding current as well as its standard deviation has been calculated and analysed to investigate their relation with the stability of electric arc and welding process. The extensive experimental and calculated results show that the approximate entropy of welding current is significantly and positively correlated with arc and welding process stability, whereas its standard deviation is correlated with them negatively. A larger approximate entropy and a smaller standard deviation imply a more stable arc and welding process, and vice versa. As a result, the approximate entropy of welding current promises well in assessing and quantifying the stability of electric arc and welding process in short-circuiting gas metal arc welding.

Keyhole Double-Sided Arc Welding Process

In the proposed method, the current/arc is guided through the keyhole so that the energy of the plasma jet is compensated while it is consumed in heating the workpiece along the keyhole. As a result, deep narrow penetration has been achieved on 12.7 mm (1/2') thick stainless steel plates using 70 A welding current.

Diffusion welding process and joint's microstructure behavior of SiC_w/6061Al composite

The rules such as process parameters affecting joint properties and theevolution principle of weld's microstructure have been researched by adopting diffusion weldingprocess to connect SiC_w/6061Al composite. Experimental results show that there exists a criticaltemperature region between solid and liquid phase line of SiC_w/6061Al composite, and the regionwill shrink with the increasing of welding pressure. When diffusion welding occurred under thecritical temperature region, welding joint exhibits bad property of bonding, and the matrix and thereinforcement can't bond effectively. When diffusion welding occurred in the critical temperatureregion, the strength of welding joint changes widely with the variation of welding temperature. Whenwelding temperature varies in 10 deg C, the strength of welding joint will change obviously. Onlywhen welding temperature is higher than the critical temperature region, stable joint properties canbe obtained. Simultaneously the matrix and the reinforcement has better interfacial bonded indiffusion welding interface, and no obvious interface reaction occurred, and thus diffusion weldingof SiC_w/6061 Al composite can be successfully realized.

A Generalized Rough Set Modeling Method for Welding Process

Modeling is essential, significant and difficult for the quality and shaping control of arc welding process. A generalized rough set based modeling method was brought forward and a dynamic predictive model for pulsed gas tungsten arc welding (GTAW) was obtained by this modeling method. The results show that this modeling method can well acquire knowledge in welding and satisfy the real life application. In addition, the results of comparison between classic rough set model and back-propagation neural network model respectively are also satisfying.

Statistical Analyses of the Effects of Welding Processes on Load, Extension and Hardness Properties of Welded Mild Steel Plates

Mild steel plates of thicknesses 0.5 mm,0.6 mm,0.7 mm,0.8 mm,0.9 mm and 1.0 mm were prepared as test samples.After welding with the developed welding robot and manual electric arc welding machine these test samples were subjected to Tensile Strength and Hardness tests.All data obtained including hardness,load and extension were analyzed and the data produced from electric arc welding operations,the robot welding operations and un-welded plates(control)were compared with one another.The statistical analyses of hardness,load and extension tests for developed welding robot,manual electric arc welding and un-welded(control)mild steel plates of different thicknesses were carried out.The results revealed that for hardness,the developed robot welding has the highest mean value of 115.30,standard deviation value of 14.32 and variance value of 205.06.The descriptive statistics of the load showed that the developed robot welding samples collectively have the lowest mean value of 2,536.85,standard deviation value of 704.21 and variance value of 495,911.72.The descriptive statistics of the extension in which the developed robot welding samples collectively have the lowest mean value of 1.29,standard deviation value of 0.43 and variance value of 0.18 were also determined.The result for hardness showed homogeneity of variance among hardness tests of the samples,which implies variation in the hardness test among the tests of the samples since p-value is 0.038.While the result for loads shows homogeneity of variance among loads of the samples in which the result reveals that there is no variation in the loads among the tests of the samples since p-value is 0.322.The result for extension shows homogeneity of variance among extensions of the samples in which it revealed that there is variation in the extensions among the tests of the samples since p-value is 0.011.The analysis of variance(ANOVA)test result revealed that there is a significant difference in the hardness of the samples in which developed robot welding operation gave the highest hardness compared with electric arc welding and un-welded(CONTROL)since p-value is 0.028.The ANOVA test result for load revealed that there is no significant difference in the loads of the samples since p-value is 0.51.The ANOVA test result of the extension shows that there is a significant difference in the extension of the samples in which developed robot welding operation gave the lowest extension compared with electric arc welding and un-welded(CONTROL)since p-value is 0.001.The results of hardness also showed the mean difference of 16.48 between developed robot welding and un-welded(CONTROL)samples and 7.26 between developed robot welding and electric arc welding samples.Finally,for extension the mean difference of-5.28 between developed robot welding and un-welded(CONTROL)samples and-1.22 between developed robot welding and electric arc welding samples were established.

The Mesozoic Welding Process between South and North Dabie Blocks：An Evidence from Pb Isotopes of Yanshanian Granites

The Pb isotope compositions of K-feldspar in granites is paid more and more geologists'attention,due to their importance of tracer.It is a fact that South Dabie Block(SDB)and North Dabie Block(NDB)had exited since Indosinian epoch(Wang et al.,1992;Cong et al,1994;Zhai et al.,1995;Chen et al.1995;Zhang et al,1996,Wang et al,1997).However,the welding process between SDB

Repair welding process of friction stir welding groove defect

The groove defect formed in the friction stir welding dramatically deteriorates weld appearances and mechanical properties of the joints owing to its larger size and penetration. Therefore, the friction stir repair welding was utilized to remove such a groove defect, and the focus was placed on the mechanical properties and microstructural characteristics of the repair joints so as to obtain an optimum repair welding process. The experimental results indicate that the groove defect can be removed by friction stir repair welding, and the offset repair welding process is superior to the symmetrical repair welding process. In the symmetrical repair welding process, a large number of fine cavity defects and an obvious aggregation of hard-brittle phase Al2Cu occur, accordingly the mechanical properties of the repair joint are weakened, and the fracture feature of repair joint is partially brittle and partially plastic. A good-quality repair joint can be obtained by the offset repair welding process, and the repair joint is fractured near the interface between the weld nugget zone and thermal-mechanically affected zone.

Optimization of Gas Metal Arc Welding Process Parameters Using Standard Deviation (SDV) and Multi-Objective Optimization on the Basis of Ratio Analysis (MOORA)

Welding technology is very vital for the industrial development and technological advancement of any country. In this regard achieving good quality machine manufactured products cannot be over emphasized. Since welding is a very reliable method of joining metals together permanently, several methodologies have been adopted to improve the quality of weldments, such as the neural network, fuzzy logic, surface response methodology, full factorial method, and so on. In this case, the multi-objective optimization on the basis of ratio analysis (MOORA) is applied. MOORA is used to solve multi-criteria (objective) optimization problem in welding. MOORA in combination with standard deviation (SDV) was used for the optimization process. SDV was used to determine the weights that were used for normalizing the responses obtained from the mechanical test results. From applying the SDV-MOORA method, it was found that welding current of 350 A, welding voltage of 22 V, an electrode diameter of 3.2 mm and welding speed of 100 mm/s produced the weldment with the best mechanical properties. The mechanical properties compare very well with those obtained from other literature. It is, therefore, concluded that the SDV-MOORA method has successfully optimized the welding process parameters used in this study.

Effect of welding processes and consumables on fatigue crack growth behaviour of armour grade quenched and tempered steel joints

Quenched and Tempered(Q&T) steels are widely used in the construction of military vehicles due to its high strength to weight ratio and high hardness. These steels are prone to hydrogen induced cracking(HIC) in the heat affected zone(HAZ) after welding. The use of austenitic stainless steel(ASS) consumables to weld the above steel was the only available remedy because of higher solubility for hydrogen in austenitic phase. The use of stainless steel consumables for a non-stainless steel base metal is not economical. Hence, alternate consumables for welding Q&T steels and their vulnerability to HIC need to be explored. Recent studies proved that low hydrogen ferritic steel(LHF) consumables can be used to weld Q&T steels, which can give very low hydrogen levels in the weld deposits. The use of ASS and LHF consumables will lead to distinct microstructures in their respective welds. This microstructural heterogeneity will have a drastic influence in the fatigue crack growth resistance of armour grade Q&T steel welds. Hence, in this investigation an attempt has been made to study the influence of welding consumables and welding processes on fatigue crack growth behaviour of armour grade Q&T Steel joints. Shielded metal arc welding(SMAW) and Flux cored arc welding(FCAW) were used for fabrication of joints using ASS and LHF consumables. The joints fabricated by SMAW process using LHF consumable exhibited superior fatigue crack growth resistance than all other joints.

Real-time monitoring of weld penetration quality in robotic arc welding process

It is of great significance to develop an intelligent monitoring system for weld penetration defects such as incomplete penetration and burn-through in real-time during robotic arc welding process. In this paper, robotic gas metal arc welding experiments are carried out on the mild steel test pieces with Vee-type groove. Through-the-arc sensing method is used to capture the transient values of the welding voltage and current. The raw data of the captured welding current and voltage are processed statistically, and the feature vector SIO is extracted to correlate the welding conditions to the weld penetration information. It lays foundation for intelligent monitoring of weld quality in robotic arc welding.

Numerical Simulation of Electromagnetic Force in Double-Sided Arc Welding Process

Up till now, most of the researchers believe that there are four kinds of forces in the weld pool convection, they aresurface tension, electromagnetic force, buoyancy and gas shear stress. So electromagnetic force is very important,especially when large current is applied. In most of previous models, the electromagnetic force is calculated analytically,in which only the axial component of current is considered. Actually the radial component of current has thesame effect, and may be advanced in some locations. In double-sided arc welding process, instead of the earthclamp, another torch is placed on the opposite side; the current will go from one torch, through the weld zone,to another torch. In this case, the current is more concentrated in the weld zone; the electromagnetic force willhave significant effect compared with conventional welding process. In this paper, a new method of numericalcalculation for electromagnetic force is developed, in which both axial and radial components are considered. And asan example, the distribution of electromagnetic force in double-sided arc welding is calculated. It demonstrates thatthis new method could give more accurate simulation of electromagnetic force, and is close to the actual process.

Measurement of Collision Conditions in Magnetic Pulse Welding Processes

MPW （magnetic pulse welding） is a solid state joining technology that allows for the generation of strong metallic bonds, even between dissimilar metals. Due to the absence of external heat, critical intermetallic phases can largely be avoided. In this process, Lorentz forces are utilized for the rapid acceleration of at least one of the two metallic joining partners leading to the controlled high velocity impact between them. The measurement of the collision conditions and their targeted manipulation are the key factors of a successful process development. Optical measuring techniques are preferred, since they are not influenced by the prevalent strong magnetic field in the vicinity of the working coil. In this paper, the characteristic high velocity impact flash during MPW was monitored and evaluated using phototransistors in order to measure the time of the impact. The results are in good accordance with the established PDV （photon Doppler velocimetry） and show a good repeatability. Furthermore, the collision front velocity was investigated using adapted part geometries within a series of tests. This velocity component is one of the key parameters in MPW; its value decreases along the weld zone. With the help of this newly introduced measurement tool, the magnetic pressure distribution or the joining geometry can be adjusted more effectively.

The Studies of the Welding Processes and Procedures on the West-East Pipeline Project

The West East pipeline project attracted the attention from all over the world for its long distance, huge diameter, complex geographic conditions, and diversified welding techniques being applied.In this paper the detail welding process and procedures used in the project are discussed and the distinguished achievements on welding techniques of China pipeline construction are described.

Effect of process parameters on the morphology of aluminum/copper alloy lap joints by red and blue hybrid laser welding

In order to overcome the problems of many pores,large deformation and unstable weld quality of traditional laser welded aluminumcopper alloy joints,a red-blue dual-beam laser source and a swinging laser were introduced for welding.T2 copper and 6063 aluminum thin plates were lap welded by coaxial dual-beam laser welding.The morphology of weld cross section was compared to explore the influence of process parameters on the formation of lap joints.The microstructure characteristics of the weld zone were observed and compared by optical microscope.The results show that the addition of laser beam swing can eliminate the internal pores of the weld.With the increase of the swing width,the weld depth decreases,and the weld width increases first and then decreases.The influence of welding speed on the weld cross section morphology is similar to that of swing width.With the increase of welding speed,the weld width increases first and then decreases,while the weld depth decreases all the time.This is because that the red laser is used as the main heat source to melt the base metals,with the increase of red laser power,the weld depth increases.As an auxiliary laser source,blue laser reduces the total energy consumption,consequently,the effective heat input increases and the spatter is restrained effectively.As a result,the increase of red laser power has an enhancement effect on the weld width and weld depth.When the swing width is 1.2 mm,the red laser power is 550 W,the blue laser power is 500 W,and the welding speed is 35 mm/s,the weld forming is the best.The lap joint of T2 copper and 6063 aluminum alloy thin plate can be connected stably with the hybrid of blue laser.The effect rules of laser beam swing on the weld formation were obtained,which improved the quality of the joints.

Research on Welding Quality Traceability Model of Offshore Platform Block Construction Process

Quality traceability plays an essential role in assembling and welding offshore platform blocks.The improvement of the welding quality traceability system is conducive to improving the durability of the offshore platform and the process level of the offshore industry.Currently,qualitymanagement remains in the era of primary information,and there is a lack of effective tracking and recording of welding quality data.When welding defects are encountered,it is difficult to rapidly and accurately determine the root cause of the problem from various complexities and scattered quality data.In this paper,a composite welding quality traceability model for offshore platform block construction process is proposed,it contains the quality early-warning method based on long short-term memory and quality data backtracking query optimization algorithm.By fulfilling the training of the early-warning model and the implementation of the query optimization algorithm,the quality traceability model has the ability to assist enterprises in realizing the rapid identification and positioning of quality problems.Furthermore,the model and the quality traceability algorithm are checked by cases in actual working conditions.Verification analyses suggest that the proposed early-warningmodel for welding quality and the algorithmfor optimizing backtracking requests are effective and can be applied to the actual construction process.

Study on gas metal arc welding of two types of TMCP steels

Gas metal arc welding experiments were conducted on two types of steels with 0.41% carbon equivalent(Ceq) and 0.31% Cequsing WER70T wire and 20% CO_(2)and 80% Ar as shielding gas.The two types of steels show satisfactory weldability.The transition temperatures of 50% upper shelf energy(Tk0.5) for Charpy-V impact test of both the welded joints are below-40 ℃.However, the toughness of the fusion line zone and heat-affected zone(HAZ) of the two steel joints exhibits differences, with the toughness of 0.41% Ceqsteel being better than that of 0.31% Ceqsteel.The Tk0.5of the fusion line zone and the HAZ of 0.41% Ceqsteel is below-60℃,whereas that of 0.31% Ceqsteel is above-40℃.The welded joint of 0.41% Ceqsteel has low hardness fluctuation, while that of 0.31% Ceqsteel exhibits a narrow, softened zone, which has no obvious influence on the tested tensile strength.The coarse grain heat-affected zone(CGHAZ)microstructure of 0.41% Ceqsteel is bainite, while that of 0.31% Ceqsteel is bainite with ferrite and minor pearlite.

Effect of Welding Processes and Consumables on Tensile and Impact Properties of High Strength Quenched and Tempered Steel Joints

Quenched and tempered steels are prone to hydrogen induced cracking in the heat affected zone after welding. The use of austenitic stainless steel consumables to weld the above steel was the only available remedy because of higher solubility for hydrogen in austenitic phase. In this investigation, an attempt was made to determine a suitable consumable to replace expensive austenitic consumables. Two different consumables, namely, austenitie stain less steel and low hydrogen ferritic steel, were used to fabricate the joints by shielded metal are welding （SMAW） and flux cored arc welding （FCAW） processes. The joints fabricated by using low hydrogen ferritic steel consumables showed superior transverse tensile properties, whereas joints fabricated by using austenitic stainless steel consumables exhibited better impact toughness, irrespective of the welding process used. The SMAW joints exhibited superior mechanical and impact properties, irrespective of the consumables used, than their FCAW counterparts.