Dilution Optimization of Laser Cladding Assisted by Pulsed Current Based on Genetic Algorithm and Neural Network

2021 ◽  
Vol 904 ◽  
pp. 485-497
Author(s):  
Dong Sheng Wang ◽  
Xin Yu Zheng ◽  
Jing Wen Wang ◽  
Xing Hua Zhou
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Laser Power ◽  
Pulse Width ◽  
Feeding Rate ◽  
Scanning Speed ◽  
Pulse Frequency ◽  
Pulsed Current ◽  
Dilution Ratio ◽  
Technological Parameters

The dilution ratio of the Ni coating prepared by the laser cladding under the assistance of the follow-up feeding pulsed current was optimized by combining back propagation (BP) neural network and genetic algorithm. The model was trained according to the results of the 6-factor 3-level orthogonal experiments. A BP genetic neural network forecast model between cladding parameters (laser power, scanning speed, powder feeding rate, pulsed current, pulse frequency and pulse width) and dilution ratio of coating was constructed. On this basis, technological parameters under the target dilution ratio of the coating were optimized by a genetic algorithm. Results demonstrated that the predicted results of the model are very close to the experimental results in term of dilution ratio of the coating, with a relative error no higher than 2.63%. This demonstrates that the model is reliable and effective. The optimal technological parameters are gained when the dilution ratio of the coating is 17.5%, including laser power=1926.3 W, laser scanning speed =·s-1, powder feeding rate= ·min-1, average pulsed current =, pulse frequency=445.6 Hz, pulse width= 108.4 μs.

scholarly journals Optimization of laser cladding process for additive repair of high temperature and high pressure valve sealing surface

2019 ◽  
Author(s):  
Lei Che
Keyword(s):  
High Pressure ◽  
Corrosion Resistance ◽  
High Temperature ◽  
Laser Cladding ◽  
Laser Power ◽  
Feeding Rate ◽  
Scanning Speed ◽  
Alloy Layer ◽  
Laser Cladding Process ◽  
Valve Sealing

Laser cladding technology is highly suitable for the remanufacturing of thin-walled and easily deformable parts due to its concentrated energy density. Due to the high temperature and high pressure corrosion environment, the valve sealing surface is prone to corrosion, wear and other failures. A nickel-based tungsten carbide alloy layer was prepared on the valve sealing surface substrate material by laser cladding process. By designing orthogonal experiments, the effects of laser power (P), scanning speed (Vb), powder feeding rate (Vf), and WC content (wt%) on the alloy layer were investigated. A fuzzy comprehensive evaluation method including macroscopic quality, microstructure, microhardness, anti-wear performance, oxidation resistance, compactness and corrosion resistance was proposed. The experimental results showed that the hardness, oxidation resistance and corrosion resistance of the laser alloy layer are significantly improved compared with the matrix; the optimum process parameters and the addition ratio of WC powder are laser power (P) of 1.1 kW and scanning speed (Vb) of 800 mm/min. The powder feeding rate (Vf) was 20%, and the WC content was 20% by weight.

Experimental Study on Pore-Defect by Selective Laser Melting of 316L Stainless Steel

2019 ◽  
Vol 801 ◽  
pp. 239-244
Author(s):  
Xin Yu Liu ◽  
Lu Pan ◽  
Wen Hao Wang ◽  
Si Yao Li
Keyword(s):  
Stainless Steel ◽  
Energy Density ◽  
Laser Power ◽  
316L Stainless Steel ◽  
Scanning Speed ◽  
Micro Structure ◽  
Technological Parameters ◽  
Product Density ◽  
Air Bubble ◽  
Test Verification

With different process parameters (laser power, scanning speed and scanning distance),the low-time defects of forming part were studied by microscope,including air bubble, pore, micro-crack and macro-crack. The formation mechanism of pore-defect was analyzed. The micro-structure and composition of the pore-defect were studied by means of SEM and EDS. The results showed that the porosity mainly included circular air porosity, irregular process porosity and oxide inclusion.Linear energy density (E=P/v) was introduced as synthetic parameter.According to analysis and test verification, the optimum technological parameters of 316L stainless steel were laser power 190-210KW, laser speed 800-1000mm/s and scanning interval 0.9-0.11mm,and the linear energy density was about 200J/m. There were no cracks, no bubbles, a small amount of porosity, and the product density reached 99.7%.

Research on Technics of Laser Direct Metal Deposition Forming Technology

2009 ◽  
Vol 69-70 ◽  
pp. 54-58
Author(s):  
Wei Zhang ◽  
Jian Hua Yao
Keyword(s):  
Laser Power ◽  
Scanning Speed ◽  
Metal Deposition ◽  
Direct Metal Deposition ◽  
Solidification Velocity ◽  
Technological Parameters ◽  
Technical Parameters ◽  
Forming Technology ◽  
Average Hardness ◽  
Feeding Speed

The technological parameters of laser direct metal deposition (DMD) were researched by DMD forming experiments using 2Cr13 powder. Fixing other parameters, the lower of laser power, the smaller the characteristic sizes of cladding layer are. Increasing of laser power, cladding height would firstly increase and then decrease, cladding width would firstly increase and then almost maintain constant, while cladding depth would gradually increase. When other parameters are invariable, with increasing of powder feeding speed, cladding height would increase, cladding width and cladding depth would decrease. When other parameters are invariable, cladding width, cladding height and cladding depth would decrease with the adding of scanning speed. The microstructure of single track cladding had three typical patterns, cellular dendritic, column dendritic and equiaxed crystal. The patterns depended on the temperature gradient and the solidification velocity. Under different technical parameters, the average hardness of specimens would change from 300HV0.2 to 550HV0.2.

Optimization of process parameters of Nd:YAG laser microgrooving of Al2TiO5 ceramic material by response surface methodology and artificial neural network algorithm

2007 ◽  
Vol 221 (8) ◽  
pp. 1341-1350 ◽  
Author(s):  
D Dhupal ◽  
B Doloi ◽  
B Bhattacharyya
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Response Surface Methodology ◽  
Predictive Model ◽  
Nd:Yag Laser ◽  
Pulse Width ◽  
Cutting Speed ◽  
Pulse Frequency ◽  
Pulsed Nd:Yag Laser ◽  
Lamp Current

The high-intensity pulsed Nd:YAG laser has the capability to produce both deep grooves and microgrooves on a wide range of engineering materials such as ceramics, composites, and diamond. The micromachining of ceramics is highly demanded in industry because of its wide and potential uses in various fields such as automobile, electronic, aerospace, and biomedical engineering. Engineering ceramic, i.e. aluminium titanate (Al2TiO5), has tremendous application in the automobile and aero-engine industries owing to its excellent thermal properties. The present paper deals with the artificial neural network (ANN) and response surface methodology (RSM) based mathematical modelling and also an optimization analysis of the machining characteristics of the pulsed Nd:YAG laser during the microgrooving operation on Al2TiO5. The experiments were planned and carried out based on design of experiments (DOE). Lamp current, pulse frequency, pulse width, assist air pressure, and cutting speed were considered as machining process parameters during the pulsed Nd:YAG laser microgrooving operation and these parameters were also utilized to develop the ANN predictive model. The response criteria selected for optimization were upper width, lower width, and depth of the trapezoidal microgroove. The optimal process parameter settings were obtained as an assist air pressure of 1.2944 kgf/cm2, lamp current of 19.3070A, pulse frequency of 1.755 kHz, pulse width of 5.7087 per cent of duty cycle, and cutting speed of 10mm/s for achieving the desired upper width, lower width, and depth of the laser microgroove. The output of the RSM optimal data was validated through experimentation and the ANN predictive model. A good agreement is observed between the results based on the ANN predictive model and the actual experimental observations.

Parametric Study of Pulsed CO2 Laser Surface Treatment of Alumina Ceramics

2015 ◽  
Vol 15 (3) ◽  
pp. 301-308
Author(s):  
A. Bharatish ◽  
H. N. Narasimha Murthy ◽  
Ajithkumar Radder ◽  
V. Mamatha ◽  
B. Anand ◽  
...  
Keyword(s):  
Surface Roughness ◽  
Material Removal Rate ◽  
Laser Power ◽  
Material Removal ◽  
Removal Rate ◽  
Scanning Speed ◽  
Pulse Frequency ◽  
Alumina Ceramics ◽  
Laser Surface Treatment ◽  
Grey Relational

AbstractThis paper focuses on investigating the influence of laser power, pulse frequency and scanning speed on material removal rate and surface roughness during CO2 laser surface treatment of alumina ceramics. Pulse frequency and laser power were the significant factors influencing the material removal rate and surface roughness, respectively. Adequate response surface models were established to correlate the laser parameters and the measured responses. Grey relational analysis predicted the optimal responses at 90 W laser power, 5 kHz pulse frequency and 400 mm/s scanning speed. Desirability function based Multi objective optimization results indicated that minimum material removal rate (0.5117 mm3/s) and surface roughness (0.5968 µm) are achieved at 90 W laser power, 5 kHz pulse frequency and 337.37 mm/s scanning speed which were in close agreement with Grey Relational results. Increase in homogeneity and smoothness of the laser treated alumina surface along with formation of micro recast particles away from the laser traverse path were evidenced by the SEM micrographs.

scholarly journals Crack Sensitivity Control of Nickel-Based Laser Coating Based on Genetic Algorithm and Neural Network

Coatings ◽  
2019 ◽  
Vol 9 (11) ◽  
pp. 728 ◽  
Author(s):  
Yu ◽  
Sun ◽  
Huang ◽  
Wang ◽  
Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Laser Cladding ◽  
Process Parameters ◽  
Feed Rate ◽  
Crack Density ◽  
Scanning Speed ◽  
Powder Feed Rate ◽  
Powder Feed ◽  
Overlap Rate

This paper aimed to establish a nonlinear relationship between laser cladding process parameters and the crack density of a high-hardness, nickel-based laser cladding layer, and to control the cracking of the cladding layer via an intelligent algorithm. By using three main process parameters (overlap rate, powder feed rate, and scanning speed), an orthogonal experiment was designed, and the experimental results were used as training and testing datasets for a neural network. A neural network prediction model between the laser cladding process parameters and coating crack density was established, and a genetic algorithm was used to optimize the prediction results. To improve their prediction accuracy, genetic algorithms were used to optimize the weights and thresholds of the neural networks. In addition, the performance of the neural network was tested. The results show that the order of influence on the coating crack sensitivity was as follows: overlap rate > powder feed rate > scanning speed. The relative error between the predicted value and the experimental value of the three-group test genetic algorithm-optimized neural network model was less than 9.8%. The genetic algorithm optimized the predicted results, and the technological parameters that resulted in the smallest crack density were as follows: powder feed rate of 15.0726 g/min, overlap rate of 49.797%, scanning speed of 5.9275 mm/s, crack density of 0.001272 mm/mm2. Therefore, the amount of crack generation was controlled by the optimization of the neural network and genetic algorithm process.

scholarly journals Research on the Effect of Key Technological Parameters on Molten Pool during Selective Laser Melting Processing

2021 ◽  
Vol 2097 (1) ◽  
pp. 012016
Author(s):  
Wentong Wang ◽  
Linfeng Tang ◽  
Congyan Chen ◽  
Yu Li ◽  
Tao Zhou
Keyword(s):  
Temperature Field ◽  
Selective Laser Melting ◽  
Molten Pool ◽  
Laser Power ◽  
Reference Value ◽  
Scanning Speed ◽  
Ansys Software ◽  
Technological Parameters ◽  
Laser Melting ◽  
Forming Process

Abstract Selective laser melting (SLM), as an emerging technology in additive manufacturing, often has various defects in the forming process. To ensure the consistency and stability of the parts forming quality, the effects of two typical technological parameters, laser power and scanning speed, on the temperature of molten pool are investigated in this paper. Firstly, the temperature field of Ti-6Al-4V is simulated theoretically via ANSYS software, and the effects of two typical technological parameters on the temperature field are studied. Then, in the experiment, using the designed radiation monitoring device and Ti-6Al-4V powder as forming material, the influence of these two typical factors on the state of molten pool is studied. The simulation and experimental results show that the temperature of molten pool shows positive correlation with the laser power and negative correlation with the scanning speed. This will provide a certain reference value for upgrading and optimizing SLM equipment.

Microstructure and properties of a laser cladded NiCrBSi alloy coating

2020 ◽  
Vol 62 (7) ◽  
pp. 698-702
Author(s):  
L. Yinghua ◽  
W. Kaiming
Keyword(s):  
Dilution Rate ◽  
Laser Power ◽  
Feeding Rate ◽  
Scanning Speed ◽  
Alloy Coating ◽  
Processing Parameters ◽  
Powder Feed Rate ◽  
Cladding Layer ◽  
Metallurgical Bonding ◽  
Scanning Electron

Abstract Laser cladded NiCrBSi alloy coating was fabricated on the surface of a 42CrMo roll using a 6 kW fiber laser. The effects of the laser power, scanning speed and feeding rate on the cladding layer form, size, dilution rate, microstructure, and hardness of coating were studied by using optical microscopy (OM), scanning electron microscopy (SEM) and a microhardness tester. The results show that the microstructure, size, dilution rate and hardness of the cladding layer had changed with an increase in laser power, powder feeding rate and scanning speed. The appropriate parameters of the laser cladding experiment are as follows: the laser power is 2000 W, powder feed rate 20 g × min-1, the scanning speed 4 mm × s-1. The cladding layer and the substrate exhibit good metallurgical bonding under the above processing parameters. The microstructure of the cladding layer is fine, the dilution rate is 9.8 wt.-%, and the microhardness of the cladding layer is 710.7 HV.

Intelligent Optimization of Optimal Operating Mode in the Production Process of Copper Converter

2014 ◽  
Vol 1022 ◽  
pp. 361-367
Author(s):  
Yi Yuan Shao ◽  
Wen Bin Liu
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Operating Mode ◽  
Technological Parameters ◽  
Optimal Operating ◽  
Intelligent Optimization ◽  
Copper Converter ◽  
Operating Modes ◽  
On Line ◽  
Chaos Genetic Algorithm

In order to enhance the standard of copper converter operation,operating modes are employed to describe a group of operating parameters which need to be decided on line, and an intelligent optimization way based on neural network and improved chaos genetic algorithm for operating modes is presented. At first, the optimal samples is sieved from the historical sample set. Secondly, the functional relationship with optimization objective and technological parameters is drilled by a neural network model. At last, chaos genetic algorithm with chaotic variables is adopted to seek the optimal operating mode. This method is applied to real-time optimization of copper converter operating parameters.The running results show that the yield of converter raises by 5.9%, and the quantity of the disposed cool materials increases by 7.7%.

Sign in / Sign up

Export Citation Format

Share Document