scholarly journals Adaptive Intelligent Welding Manufacturing

2021 ◽  
Vol 100 (01) ◽  
pp. 63-83
Author(s):  
YUMING ZHANG ◽  
◽  
QIYUE WANG ◽  
YUKANG LIU
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Deep Learning ◽  
Welding Process ◽  
Welding Parameters ◽  
Weld Quality ◽  
Robotic Welding ◽  
Process Variables ◽  
Physical Constraints ◽  
Needed Information

Optimal design of the welding procedure gives the desired welding results under nominal welding conditions. During manufacturing, where the actual welding manufacturing conditions often deviate from the nominal ones used in the design, applying the designed procedure will produce welding results that are different from the desired ones. Adaption is needed to make corrections and adjust some of the welding parameters from those specified in the design. This is adaptive welding. While human welders can be adaptive to make corrections and adjustments, their performance is limited by their physical constraints and skill level. To be adaptive, automated and robotic welding systems require abilities in sensing the welding process, extracting the needed information from signals from the sensors, predicting the responses of the welding process to the adjustments on welding parameters, and optimizing the adjustments. This results in the application of classical sensing, modeling of process dynamics, and control system design. In many cases, the needed information for the weld quality and process variables of our concern is not easy to extract from the sensor’s data. Studies are needed to propose the phenomena to sense and establish the scientific foundation to correlate them to the weld quality or process variables of our concern. Such studies can be labor intensive, and a more automated approach is needed. Analysis suggests that artificial intelligence and machine learning, especially deep learning, can help automate the learning such that the needed intelligence for robotic welding adaptation can be directly and automatically learned from experimental data after the physical phenomena being represented by the experimental data has been appropriately selected to make sure they are fundamentally correlated to that with which we are concerned. Some adaptation abilities may also be learned from skilled human welders. In addition, human-robot collaborative welding may incorporate adaptations from humans with the welding robots. This paper analyzes and identifies the challenges in adaptive robotic welding, reviews efforts devoted to solve these challenges, analyzes the principles and nature of the methods behind these efforts, and introduces modern approaches, including machine learning/deep learning, learning from humans, and human-robot collaboration, to solve these challenges.

scholarly journals Online programming system for robotic fillet welding in Industry 4.0

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ignacio Diaz-Cano ◽  
Fernando M. Quintana ◽  
Miguel Lopez-Fuster ◽  
Francisco-Javier Badesa ◽  
Pedro L. Galindo ◽  
...  
Keyword(s):  
Industry 4.0 ◽  
Industrial Revolution ◽  
Low Cost ◽  
Welding Process ◽  
Robot Programming ◽  
Welding Parameters ◽  
Programming System ◽  
Robotic Welding ◽  
Content Type ◽  
Fillet Welding

Purpose Fillet welding is one of the most widespread types of welding in the industry, which is still carried out manually or automated by contact. This paper aims to describe an online programming system for noncontact fillet welding robots with “U”- and “L”-shaped structures, which responds to the needs of the Fourth Industrial Revolution. Design/methodology/approach In this paper, the authors propose an online robot programming methodology that eliminates unnecessary steps traditionally performed in robotic welding, so that the operator only performs three steps to complete the welding task. First, choose the piece to weld. Then, enter the welding parameters. Finally, it sends the automatically generated program to the robot. Findings The system finally managed to perform the fillet welding task with the proposed method in a more efficient preparation time than the compared methods. For this, a reduced number of components was used compared to other systems: a structured light 3 D camera, two computers and a concentrator, in addition to the six-axis industrial robotic arm. The operating complexity of the system has been reduced as much as possible. Practical implications To the best of the authors’ knowledge, there is no scientific or commercial evidence of an online robot programming system capable of performing a fillet welding process, simplifying the process so that it is completely transparent for the operator and framed in the Industry 4.0 paradigm. Its commercial potential lies mainly in its simple and low-cost implementation in a flexible system capable of adapting to any industrial fillet welding job and to any support that can accommodate it. Originality/value In this study, a robotic robust system is achieved, aligned to Industry 4.0, with a friendly, intuitive and simple interface for an operator who does not need to have knowledge of industrial robotics, allowing him to perform a fillet welding saving time and increasing productivity.

Application of Microcomputers to Automatic Weld Quality Control

1980 ◽  
Vol 102 (2) ◽  
pp. 62-68 ◽  
Author(s):  
M. Tomizuka ◽  
D. Dornfeld ◽  
M. Purcell
Keyword(s):  
Control Method ◽  
Computer Control ◽  
Gas Metal Arc Welding ◽  
Welding Process ◽  
Seam Tracking ◽  
Process Time ◽  
Welding Parameters ◽  
Weld Quality ◽  
On Line ◽  
Welding Processes

The demand for increased productivity of welding operations has led to the expanded use of computer control to allow higher production rates while maintaining weld quality. The charateristics of the gas metal arc welding process and the relationship between welding parameters, the desired output of the welding process, and the automation of the process are discussed. A strategy for two-axis welding torch positioning and velocity control is developed based on preview control techniques. To evaluate the applicability of the proposed control method the motion of heat source along different welding paths is simulated on an analog computer with on-line control of process time constants by an LSI-11 microcomputer. The simulation results show that high quality seam tracking can be accomplished by controlling the torch motion using the proposed method. The method appears to be suitable for on-line control of welding processes.

Microstructure and Mechanical Properties of Friction Stir Welded AA6060-T6 Tubes

2013 ◽  
Vol 554-557 ◽  
pp. 977-984 ◽  
Author(s):  
Gianluca D'Urso ◽  
Michela Longo ◽  
Claudio Giardini
Keyword(s):  
Welding Process ◽  
Tensile Tests ◽  
Fusion Welding ◽  
Welding Parameters ◽  
External Diameter ◽  
Weld Quality ◽  
Cnc Machine ◽  
Friction Stir ◽  
Aluminum Tubes ◽  
Welding Processes

Friction stir welding (FSW) has received increasing attention in recent years thanks to its advantages over traditional welding processes, reducing distortion and eliminating solidification defects. Since melting does not take place and joining occurs below the melting temperature of the material, this welding process allows to obtain a weld characterized by very high quality with low heat input, minimal distortion, no filler material, and no fumes. FSW is also highly efficient and it is characterized by improved environmental performance if compared to traditional welding methods. For instance, FSW is particularly advantageous in the pipeline industry because this innovative welding process usually entails reduction in energy usage of up to 80% if compared to conventional fusion welding processes. Moreover, also alloys normally difficult to be welded can be considered with this technique. The objective of the present study is to establish and to study the weldability of aluminum tubes by means of FSW process. The study shows preliminary results on circumferential FSW of AA6060-T6 aluminum tubes and the influence of the welding process on weld quality. The experimental campaign was performed on tubes having a thickness equal to 5 mm and an external diameter equal to 80 mm. Tubes were welded by means of a four axes CNC machine tool. Particular care was paid to the fabrication of the inner support for the tube. The mandrel was designed in order to guarantee limited bending during the welding process. Some preliminary tests were carried out by varying the welding parameters, namely feed rate (f) and rotational speed (S). A tool having conical shoulder and cylindrical pin was used. The weld quality investigation was based on tensile tests, microhardness and macrostructure analysis of the joints.

scholarly journals Physics Informed Deep Learning for Flow and Transport in Porous Media

2021 ◽  
Author(s):  
Cedric G. Fraces ◽  
Hamdi Tchelepi
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Boundary Conditions ◽  
Initial Conditions ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Robust Solution ◽  
Physical Constraints ◽  
Physical Knowledge ◽  
Physical Laws

Abstract We present our progress on the application of physics informed deep learning to reservoir simulation problems. The model is a neural network that is jointly trained to respect governing physical laws and match boundary conditions. The methodology is hereby used to simulate a 2-phase immiscible transport problem (Buckley-Leverett). The model is able to produce an accurate physical solution both in terms of shock and rarefaction and honors the governing partial differential equation along with initial and boundary conditions. We test various hypothesis (uniform and non-uniform initial conditions) and show that with the proper implementation of physical constraints, a robust solution can be trained within a reasonable amount of time and iterations. We revisit some of the limitations presented in previous work [1] and further the applicability of this method in a forward, pure hyperbolic setup. We also share some practical findings on the application of physics informed neural networks (PINN). We review various network architectures presented in the literature and show tips that helped improve their convergence and accuracy. The proposed methodology is a simple and elegant way to instill physical knowledge to machine-learning algorithms. This alleviates the two most significant shortcomings of machine-learning algorithms: the requirement for large datasets and the reliability of extrapolation. The principles presented can be generalized in innumerable ways in the future and should lead to a new class of algorithms to solve both forward and inverse physical problems.

scholarly journals The Use of Fiberglass and Ceramic Cylinders to Support the Root Pass in C-Steel Welds with a Double-V Groove

2015 ◽  
Vol 20 (3) ◽  
pp. 359-366
Author(s):  
Ricardo Fernandes Gurgel ◽  
Ronaldo Pinheiro da Rocha Paranhos
Keyword(s):  
Carbon Steel ◽  
Welding Process ◽  
Metallurgical Industry ◽  
Travel Speed ◽  
Ceramic Fiber ◽  
Great Promise ◽  
Welding Parameters ◽  
Process Variables ◽  
Steel Welds ◽  
Welding Technique

Abstract The aim of this work is to evaluate the effectiveness of fiberglass and ceramic fiber cylinders as root-pass weld backing for a double-V groove in 16 mm-thick carbon steel. Three different cylinder diameters were tested: 4.8, 9.5 mm (fiberglass) and 6.4 mm (ceramic fiber). The welding process used was GMAW. The welding technique and the following process variables were investigated: root opening, current and travel speed. The results show that cylindrical fiberglass and ceramic fiber backings not only have excellent refractory properties, but also seal the root opening and contain the weld pool sufficiently to produce a root bead free of discontinuities and with a satisfactory shape and geometry. Working points were defined, together with a possible operating range for the welding parameters. It was concluded that cylindrical fiberglass and ceramic fiber weld backings hold great promise for use in root-pass welds in double-V grooves in applications in the naval and metallurgical industry.

Effects of bottom plate in friction stir welding of AA6061-T6

2020 ◽  
Vol 118 (1) ◽  
pp. 108
Author(s):  
M.A. Vinayagamoorthi ◽  
M. Prince ◽  
S. Balasubramanian
Keyword(s):  
Mechanical Properties ◽  
Axial Load ◽  
Weld Zone ◽  
Welding Process ◽  
Bottom Plate ◽  
Welding Parameters ◽  
Nugget Zone ◽  
Friction Stir ◽  
Weld Joints ◽  
Fine Grain

The effects of 40 mm width bottom plates on the microstructural modifications and the mechanical properties of a 6 mm thick FSW AA6061-T6 joint have been investigated. The bottom plates are placed partially at the weld zone to absorb and dissipate heat during the welding process. An axial load of 5 to 7 kN, a rotational speed of 500 rpm, and a welding speed of 50 mm/min are employed as welding parameters. The size of the nugget zone (NZ) and heat-affected zone (HAZ) in the weld joints obtained from AISI 1040 steel bottom plate is more significant than that of weld joints obtained using copper bottom plate due to lower thermal conductivity of steel. Also, the weld joints obtained using copper bottom plate have fine grain microstructure due to the dynamic recrystallization. The friction stir welded joints obtained with copper bottom plate have exhibited higher ductility of 8.9% and higher tensile strength of 172 MPa as compared to the joints obtained using a steel bottom plate.

Deep Learning Based High-Resolution Remote Sensing Image classification

2017 ◽  
Vol 7 (10) ◽  
pp. 22
Author(s):  
Sumit Kaur
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Deep Learning ◽  
Image Classification ◽  
Language Processing ◽  
Object Perception ◽  
Remote Sensing Image ◽  
Research Area ◽  
Remote Sensing Image Classification ◽  
Unsupervised Algorithms

Abstract- Deep learning is an emerging research area in machine learning and pattern recognition field which has been presented with the goal of drawing Machine Learning nearer to one of its unique objectives, Artificial Intelligence. It tries to mimic the human brain, which is capable of processing and learning from the complex input data and solving different kinds of complicated tasks well. Deep learning (DL) basically based on a set of supervised and unsupervised algorithms that attempt to model higher level abstractions in data and make it self-learning for hierarchical representation for classification. In the recent years, it has attracted much attention due to its state-of-the-art performance in diverse areas like object perception, speech recognition, computer vision, collaborative filtering and natural language processing. This paper will present a survey on different deep learning techniques for remote sensing image classification. 

Data science in economics: comprehensive review of advanced machine learning and deep learning methods

2020 ◽  
Author(s):  
Saeed Nosratabadi ◽  
Amir Mosavi ◽  
Puhong Duan ◽  
Pedram Ghamisi ◽  
Ferdinand Filip ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Data Science ◽  
State Of The Art ◽  
Science Methods ◽  
Learning Models ◽  
Diverse Range ◽  
Hybrid Machine ◽  
Economics Research

This paper provides a state-of-the-art investigation of advances in data science in emerging economic applications. The analysis was performed on novel data science methods in four individual classes of deep learning models, hybrid deep learning models, hybrid machine learning, and ensemble models. Application domains include a wide and diverse range of economics research from the stock market, marketing, and e-commerce to corporate banking and cryptocurrency. Prisma method, a systematic literature review methodology, was used to ensure the quality of the survey. The findings reveal that the trends follow the advancement of hybrid models, which, based on the accuracy metric, outperform other learning algorithms. It is further expected that the trends will converge toward the advancements of sophisticated hybrid deep learning models.

Deep Learning for text in limted data settings

2020 ◽  
Author(s):  
Pathikkumar Patel ◽  
Bhargav Lad ◽  
Jinan Fiaidhi
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Transfer Learning ◽  
Text Classification ◽  
State Of The Art ◽  
Time Series Forecasting ◽  
Text Data ◽  
Performance Levels

During the last few years, RNN models have been extensively used and they have proven to be better for sequence and text data. RNNs have achieved state-of-the-art performance levels in several applications such as text classification, sequence to sequence modelling and time series forecasting. In this article we will review different Machine Learning and Deep Learning based approaches for text data and look at the results obtained from these methods. This work also explores the use of transfer learning in NLP and how it affects the performance of models on a specific application of sentiment analysis.

Sign in / Sign up

Export Citation Format

Share Document