Feature Extraction and Dimensionality Reduction of Arc Sound under Typical Penetration Status in Metal Inert Gas Welding

Arc sound is well known as the potential and available resource for monitoring and controlling of the weld penetration status,which is very important to the welding process quality control,so any attentions have been paid to the relationships between the arc sound and welding parameters.Some non-linear mapping models correlating the arc sound to welding parameters have been established with the help of neural networks.However,the research of utilizing arc sound to monitor and diagnose welding process is still in its infancy.A self-made real-time sensing system is applied to make a study of arc sound under typical penetration status,including partial penetration,unstable penetration,full penetration and excessive penetration,in metal inert-gas（MIG） flat tailored welding with spray transfer.Arc sound is pretreated by using wavelet de-noising and short-time windowing technologies,and its characteristics,characterizing weld penetration status,of time-domain,frequency-domain,cepstrum-domain and geometric-domain are extracted.Subsequently,high-dimensional eigenvector is constructed and feature-level parameters are successfully fused utilizing the concept of primary principal component analysis（PCA）.Ultimately,60-demensional eigenvector is replaced by the synthesis of 8-demensional vector,which achieves compression for feature space and provides technical supports for pattern classification of typical penetration status with the help of arc sound in MIG welding in the future.

A NEURAL NETWORK FOR WELD PENETRATION CONTROL IN GAS TUNGSTEN ARC WELDING

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.

Penetration control by weld pool resonance during gas tungsten arc welding

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.

Determination of the maximum allowable gas pressure for an underground gas storage salt cavern——A case study of Jintan,China

Increasing the allowable gas pressure of underground gas storage(UGS) is one of the most effective methods to increase its working gas capacity. In this context, hydraulic fracturing tests are implemented on the target formation for the UGS construction of Jintan salt caverns, China, in order to obtain the minimum principal in situ stress and the fracture breakdown pressure. Based on the test results, the maximum allowable gas pressure of the Jintan UGS salt cavern is calibrated. To determine the maximum allowable gas pressure, KING-1 and KING-2 caverns are used as examples. A three-dimensional(3D)geomechanical model is established based on the sonar data of the two caverns with respect to the features of the target formation. New criteria for evaluating gas penetration failure and gas seepage are proposed. Results show that the maximum allowable gas pressure of the Jintan UGS salt cavern can be increased from 17 MPa to 18 MPa(i.e. a gradient of about 18 k Pa/m at the casing shoe depth). Based on numerical results, a field test with increasing maximum gas pressure to 18 MPa has been carried out in KING-1 cavern. Microseismic monitoring has been conducted during the test to evaluate the safety of the rock mass around the cavern. Field monitoring data show that KING-1 cavern is safe globally when the maximum gas pressure is increased from 17 MPa to 18 MPa. This shows that the geomechanical model and criteria proposed in this context for evaluating the maximum allowable gas pressure are reliable.

A novel complex network-based deep learning method for characterizing gas-liquid two-phase flow

Gas-liquid two-phase flow widely exits in production and transportation of petroleum industry.Characterizing gas-liquid flow and measuring flow parameters represent challenges of great importance,which contribute to the recognition of flow regime and the optimal design of industrial equipment.In this paper,we propose a novel complex network-based deep learning method for characterizing gas-liquid flow.Firstly,we map the multichannel measurements to multiple limited penetrable visibility graphs(LPVGs)and obtain their degree sequences as the graph representation.Based on the degree distribution,we analyze the complicated flow behavior under different flow structures.Then,we design a dual-input convolutional neural network to fuse the raw signals and the graph representation of LPVGs for the classification of flow structures and measurement of gas void fraction.We implement the model with two parallel branches with the same structure,each corresponding to one input.Each branch consists of a channel-projection convolutional part,a spatial-temporal convolutional part,a dense block and an attention module.The outputs of the two branches are concatenated and fed into several full connected layers for the classification and measurement.At last,our method achieves an accuracy of 95.3%for the classification of flow structures,and a mean squared error of 0.0038 and a mean absolute percent error of 6.3%for the measurement of gas void fraction.Our method provides a promising solution for characterizing gas-liquid flow and measuring flow parameters.

Influence of blast furnace top gas composition and dust on HCl removal with low temperature Ca-based dechlorination agent

Using fixed-bed reaction method and changing the gas composition and dust content,the influence of blast furnace top gas composition and dust on HCl removal with low temperature Ca-based antichlor was studied.It was found that,when the content of CO2 in blast furnace top gas increased,the dechlorination efficiency was getting worse obviously;when the contents of CO and N2 increased,the dechlorination efficiency was getting better to a certain extent;when the content of H2 changed,the dechlorination efficiency got no significant change;as the content of dust increased,the dechlorination efficiency got better obviously when the content was less than 15 g/m3,but it would be got worse quickly when the content was more than 20 g/m3,and the best content was 15–20 g/m3;the suitable site of the process of dechlorination was after gravity dust collector and before bag dust collector.

Effects of pulse parameters on arc characteristics and weld penetration in hybrid pulse VP-GTAW of aluminum alloy

A novel ultrafast-convert hybrid pulse variable polarity gas tungsten arc welding process （HPVP-GTAW） is developed. High frequency pulse square-wave current which has a frequency of more than 20 kHz is exactly integrated in the positive polarity current duration. The effects of pulse current parameters on arc characteristics and weld penetration have been studied during the HPVP-GTAW process using Al-5. 8 Mg alloy plates. The arc characteristics studied by arc voltage and its profile, weld penetration noted by the ratio of weld depth to width have been found to be influenced significantly by the pulse current. The experimental results show that the HPVP-GTA W process can improve the arc profile predominantly and obtain the higher weld penetration with lower heat input. The observation may help in understanding the weld characteristics with respect to variation in the pulse current parameters which may be beneficial in using the novel HPVP-GTAW process to produce the better weld quality of aluminum alloy plates.

Study of 3-D Numerical Simulation for Gas Transfer in the Goaf of the Coal Mining

In order to simulate field distribution rules,mathematical models for 3-D air flows and gas transfer in the goaf of the coal mining are established,based on theories of permeability and dynamic dispersion through porous media. A gas dispersion equation in a 3-D field is calculated by use of numerical method on a weighted upstream multi-element balance. Based on data of an example with a U type ventilation mode,surface charts of air pressure distribution and gas concentration are drawn by Graphtool software. Finally,a comparison between actually measured results in the model test and the numerical simulation results is made to proves the numerical implementation feasible.

Characteristics of Leakage Pollution of Longpan Road Gas Station and Its Enlightenment

Geological penetrating radar combined with drilling and chemical analysis has been applied to investigate leakage pollution of Longpan Road gas station in Nanjing, China. The results indicate that radar images show strong reflection anomalies along the northeast to the gas station, characterized by contaminants or contaminant plumes spreading downstream and below. The drilling results confirmed the contents of monocyclic and polycyclic aromatic hydrocarbons contained in the layers of fine sands ranging from 0.60 m to 6.0 m beneath the surface mostly exceed Chinese standard severely, such as toluene and isobutylbenzene with high content at 2738 μg/kg and 64505 μg/kg, respectively. Therefore, it is considered that geological penetrating radar can be employed to investigate leakage contamination of gas stations, and remediation and administration should be conducted in the polluted soil layers and aquifers.

Deformation and water/gas flow properties of claystone/bentonite mixtures

As a potential engineered barrier material for disposal of radioactive waste in clay formations,claystone aggregate excavated from the Opalinus clay(OPA),its mixture with bentonite MX80 in a mass ratio of 7/3,and pure bentonite were extensively investigated with respect to the hydro-mechanical properties and performances.With these materials,a series of parallel experiments was performed under sequentially applied conditions of hydration with synthetic porewater of the clay formation,consolidation and water flow under increased stresses,and gas injection into the water-saturated and compacted materials under loading.Significant responses of the clay mixtures were observed.Main findings include:(1)the hydration and induced swelling of the mixtures are mainly dominated by bentonite content and dry density;(2)the consolidation decreases the porosity and water permeability exponentially by 2-3 orders of magnitude to low values of 10^(-18)-10^(-20) m^(2) at stresses of 2-5 MPa,depending upon bentonite content;and(3)the gas penetration in the water-saturated and compacted bentonite is characterised by a cyclic pressure rising/dropping process limited in between the upper breakthrough and lower shut-off boundaries,whereas the compacted claystone and claystone/bentonite mixture allow for gas release at low and moderate pressures.The results are helpful for design of the engineered barriers for safe isolation of radioactive waste in repositories.

Characteristics of fracture development and gas extraction of a lower protected seam

To ensure the mining safety of working face in the protective seam and meanwhile extract pressure-relief gas of the lower protected seam and eliminate its outburst risk,the present study researched into fracture development of floor coal-rock mass of the protective seam and migration rule of pressure-relief gas from a protected seam so as to obtain an effective pressure- relief gas extraction method.The results show that after the upper protective seam was mined,mining-induced fracturing floor coal-rock mas...

Topology optimization of reactive material structures for penetrative projectiles

Recently,reactive materials have been developed for penetrative projectiles to improve impact resistance and energy capacity.However,the design of a reactive material structure,involving shape and size,is challenging because of difficulties such as high non-linearity of impact resistance,manufacturing limitations of reactive materials and high expenses of penetration experiments.In this study,a design optimization methodology for the reactive material structure is developed based on the finite element analysis.A finite element model for penetration analysis is introduced to save the expenses of the experiments.Impact resistance is assessed through the analysis,and result is calibrated by comparing with experimental results.Based on the model,topology optimization is introduced to determine shape of the structure.The design variables and constraints of the optimization are proposed considering the manufacturing limitations,and the optimal shape that can be manufactured by cold spraying is determined.Based on the optimal shape,size optimization is introduced to determine the geometric dimensions of the structure.As a result,optimal design of the reactive material structure and steel case of the penetrative projectile,which maximizes the impact resistance,is determined.Using the design process proposed in this study,reactive material structures can be designed considering not only mechanical performances but also manufacturing limitations,with reasonable time and cost.

Dynamic effects of high-pressure pulsed water jet in low-permeability coal seams

Mine gas extraction in China is difficult due to the characteristics such as micro-porosity,low-permeability and high adsorption of coal seams.The pulsed mechanismof a high-pressure pulsed water jet was studied through theoretical analysis,experimentand field measurement.The results show that high-pressure pulsed water jet has threedynamic properties.What's more,the three dynamic effects can be found in low-permeabilitycoal seams.A new pulsed water jet with 200-1 000 Hz oscillation frequency andpeak pressure 2.5 times than average pressure was introduced.During bubble collapsing,sound vibration and instantaneous high pressures over 100 MPa enhanced the cuttingability of the high-pressure jet.Through high-pressure pulsed water jet drilling and slotting,the exposure area of coal bodies was greatly enlarged and pressure of the coal seamsrapidly decreased.Therefore,the permeability of coal seams was improved and gas absorptionrate also decreased.Application results show that gas adsorption rate decreasedby 30%-40%and the penetrability coefficient increased 100 times.This proves that high-pressurepulsed water is more efficient than other conventional methods.

The Effects of Carbon Dioxide Laser Irradiation on Drilling of Limestone Included Crude Oil

Laser rock spallation is a rock removal process that utilizes laser induced thermal stress to fracture and cause a break through the rock by creating small fragments before melting of the rock. In this paper we investigated the effects of CO2 laser irradiation on limestone of Iran Sarvak formation. Since the limestone included heavy and light oil, we studied the amount of laser beam absorption by this oils for determining thermal fractured during the laser drilling laboratory process. In order to characterize this limestone spectrophotometry (from UV to NIR), scanning electron microscopy (SEM) have been used.

Acoustic Emission Studies on Weld Bead Defects in Nuclear Grade SS 316L Materials

This paper contributes about the behaviour of Acoustic Emission (AE) signatures of implanted weld defects of SS 316L materials. Lack of penetration and lack of side fusion defects were implanted in weld bead region of the materials. Tungsten Inert Gas Welding (TIG) is adopted to weld the Stainless Steel (SS316L) nuclear grade materials. The material is fabricated with dimensions of 140 × 16 × 10 mm and AE signatures are studied under preload conditions. Mechanical Jig is fabricated to maintain constant load in concentrated weld region. When external load is applied on the weld region, the deformed specimen experiences acoustic emission signals form the weld defect region which are potential source of releasing stress energy. Liner Location Technique (LLT) is adopted for AE singal studies and the generated signal is processed by 2-channel USB—AE node and AE-WIN software. The tests are conducted on two different samples having each defect. A conventional NDT method i.e. X-ray Radiography is conducted on the samples to know the defect ranging and correlated with AE signatures. This study will be helpful to standardize the AE signals for different implanted weld defects of SS 316L materials and it is found that, the parameter “counts vs. amplitude” has given the widest distinction with respect to the type of defects.

Real-time K-TIG welding penetration prediction on embedded system using a segmentation-LSTM model

Keyhole tungsten inert gas(K-TIG)welding is capable of realizing single-sided welding and double-sided forming and has been widely used in medium and thick plate welding.In order to improve the accuracy of automatic weld identification and weld penetration prediction of robot in the process of large workpiece welding,a two-stage model is proposed in this paper,which can monitor the K-TIG welding penetration state in real time on the embedded system,called segmentation-LSTM model.The proposed system extracts 9 weld pool geometric features with segmentation network,and then extracts the weld gap using a traditional algorithm.Then these 10-dimensional features are input into the LSTM model to predict the penetration state,including under penetration,partial penetration,good penetration and over penetration.The recognition accuracy of the proposed system can reach 95.2%.In this system,to solve the difficulty of labeling data and lack of segmentation accuracy,an improved LabelMe capable of live-wire annotation tool and a novel loss function were proposed,respectively.The latter was also called focal dice loss,which enabled the network to achieve a performance of 0.933 mloU on the testing set.Finally,an improved slimming strategy compresses the network,making the segmentation network achieve real-time on the embedded system(RK3399pro).

Stochastic Dynamic Economic Dispatch of Wind-integrated Electricity and Natural Gas Systems Considering Security Risk Constraints

As the proportion of wind power generation increases in power systems,it is necessary to develop new ways for wind power accommodation and improve the existing power dispatch model.The power-to-gas technology,which offers a new approach to accommodate surplus wind power,is an excellent way to solve the former.Hence,this paper proposes to involve power-to-gas technology in the integrated electricity and natural gas systems(IEGSs).To solve the latter,on one hand,a new indicator,the scale factor of wind power integration,is introduced into the wind power stochastic model to better describe the uncertainty of grid-connected wind power;on the other hand,for quantizing and minimizing the impact of the uncertainties of wind power and system loads on system security,security risk constraints are established for the IEGS by the conditional value-at-risk method.By considering these two aspects,an MILP formulation of a security-risk based stochastic dynamic economic dispatch model for an IEGS is established,and GUROBI obtained from GAMS is used for the solution.Case studies are conducted on an IEGS consisting of a modified IEEE 39-bus system and the Belgium 20-node natural gas system to examine the effectiveness of the proposed dispatch model.

Principles Giving High Penetration under the Double Shielded TIG Process

A new welding method named double shielded tungsten inert gas （TIG） has been developed to improve the TIG weld penetration. The main principles to increase the weld depth have been discussed. Results show that the critical oxygen content in the weld pool is around 100 × 10 -6 as the temperature coefficient of surface tension changes from negative to positive. The tracer test using pure silver shows that the direction of Marangoni convection changes as the oxygen content increases in the weld pool. The effect of arc constriction on the weld depth has been evaluated on a water-cooled copper plate, and the result indicates that the torch of double shielded can give a more powerful arc. Heavy oxide on the pool surface has undesirable impacts on the increasing of weld depth as the oxygen excessively accumulates in weld pool. It is possible to form chromium oxide in the weld process, while the iron oxide may form as the weld surface exposes to the air after the shielded gas moving away.