Real-time recognition of weld defects based on visible spectral image and machine learning

The quality of Tungsten Inert Gas welding is dependent on human supervision, which can’t suitable for automation. This study designed a model for assessing the tungsten inert gas welding quality with the potential of application in real-time. The model used the K-Nearest Neighborhood (KNN) algorithm, paired with images in the visible spectrum formed by high dynamic range camera. Firstly, projecting the image of weld defects in the training set into a two-dimensional space using multidimensional scaling (MDS), so similar weld defects was aggregated into blocks and distributed in hash, and among different weld defects has overlap. Secondly, establishing models including the KNN, CNN, SVM, CART and NB classification, to classify and recognize the weld defect images. The results show that the KNN model is the best, which has the recognition accuracy of 98%, and the average time of recognizing a single image of 33ms, and suitable for common hardware devices. It can be applied to the image recognition system of automatic welding robot to improve the intelligent level of welding robot.

Design of an universal source for semi-automatic ac welding and induction heating

This paper proposes a circuit solution and a power source control algorithm for semi-automatic AC welding with improved energy and weight-size characteristics. A distinctive feature of the designed source is the absence of an input rectifier: welding is carried out with a high-frequency alternating current. That has made it possible to significantly reduce power losses in the source, as well as provide the possibility of implementing induction heating by connecting an inductor to the source output. Another distinctive feature of the designed source is an increased power factor and a reduced level of higher harmonics of the current consumed. The power factor of the described source reaches 0.94 against 0.5÷0.7 for sources equipped with a conventional rectifier with capacitive smoothing. The designed source's composition includes a power supply system for the wire feed drive with speed stabilization due to positive feedback on the motor current. That has made it possible to ensure the stable operation of the drive in a wide range of speeds. A model has also been developed of a flux wire welding torch containing a feed drive and a coil with a wire (up to 100 mm in diameter), placed, in order to reduce the size, in the handle of the torch. In addition to the welding function, the source makes it possible to solve the tasks related to induction heating and/or hardening of small parts; to that end, a compact inductor is connected to its output. Tests of the source showed the feasibility of the proposed ideas and circuit solutions. The dimensions of the source are 190×107×65 mm; weight, 1.4 kg; output current, up to 120 A. The proposed technical solution enables the construction of small-sized, lightweight, universal, easy-to-use power supplies for semi-automatic welding with the option of induction heating

IDENTIFICATION OF INCOMPLETE PENETRATION WELDING DEFECTS ON DIGITAL RADIOGRAPHIC FILM FIGURES WITH THE GEOMETRIC INVARIANT MOMENT

The examination of defects in radiographic films necessitates specialized knowledge, as indicated by an expert radiographer (AR) degree, yet the subjectivity of AR in identifying defects is problematic. To overcome this subjectivity, an automatic welding defect identification is needed. This is executed by using Matlab to create artificial neural networks, which is beneficial for users with the graphical user interface (GUI) feature. One of the breakthroughs in the figure extraction into seven feature vector values is the geometric invariant moment theory. This prevents translation, rotation, and scaling from changing the figure's characteristics. Therefore, a welding defect identification system with a geometric invariant moment was created in the digital radiographic film figure to overcome the reading error by AR. The identification system obtained an accuracy rating of 89.9%.

Representation of gas metal arc pulsed welding process behavior on bead geometry: a study of leading variables

Gas metal arc welding is one of the most influential processes in the production and repair of structures and equipment; therefore, the need to improve the productivity and quality of welded joints has led to the development of techniques for good control of welding parameters. Also, the development of semi-automatic welding processes led to the control of one of the variables such as pulsed current; this technique is characterized by a lower heat input and lower energy expenditure, which directly influences the structural quality of the welded joint and the geometry of the weld bead. This work focused on evaluating the effects of various welding operating parameters using the central composite design tool based on the response surface methodology; next, the experimental development employed an inverter type power source for weld depositions, a commercial grade Stargold clean 96% Ar and 4% CO2 shielding gas at the rate of 15 L/min stationary arc, a 1.2 mm metal cored wire for welding deposit and a carbon steel base plate with a thickness of 6 mm. During the welding process, the torch was kept at a 90° inclination and a 16 mm stroke. To examine the adequacy of the empirical models and the significance of the regression coefficients, the variance analysis was employed. Consequently, the graphs were obtained through the determination of the model; from the statistical results obtained, it was shown that the above models were adequate to predict the weld width, bead height, and penetration within the range of variables studied. Furthermore, it was observed that the wire feed rate it has a very marked effect on weld bead geometry, followed by frequency pulse and peak current; finally, the effectiveness of employing these methodologies for the management of variables attributing to the execution of welding tasks with higher accuracy was demonstrated.

The DESIGN AND CONSTRUCTION OF ROBOTIC ARM ON AUTOMATIC MIG WELDING ROBOT

Tehnlogical advances to date have grown increasingly sophisticated technolgy, especially in robotic technogy which is currently developed to achieve work result that are make human work easier welding process with manual systems need to be switched to automatic systems. The mechanical concept of the arm that will be applied to Automatic Welding Carrier Machine by applying the mechanical concept of a 3D machine which is expected to increase mobility, working range of the tool as well as increasing the quality of automatic welding results. In this research, the method used is experimental research methods and simulations that aim to know the results of the analysis on the mechanics of the robot arm. The data generated after performing calculations with provide a load on the leadscrew of the compressive stress that occurs i the leadscrew is , the voltage bending is and the shear stress that occurs is , so that the lead crew is said to be able to encourge maximum allowable amount of . The torque required by the motor drive to push the received load on the Z ( ) axis is equal to , then the selection of the nema23 stepper motor is stated very capable as a robotic arm mover because have torque . With the loading of the 2020 profile arm rod at using ansys simulation, the maximum total deformation that may occur is , so that the 2020 profile rod can be said to be safe for use on Automatic Welding Carrier Machine.

MODERN STEEL-CONCRETE SPAN STRUCTURES OF SMALL AND MEDIUM-SPAN BRIDGES

The paper reviews the most common reinforced concrete girder structures of modern bridges used in Ukraine and other countries. The scope, advantages and disadvantages of reinforced concrete structures are considered. The peculiarities of the use of reinforced concrete structures in European countries are reviewed. The most common typical structural solutions of reinforced concrete girder structures used worldwide are given. Options for facilitation of reinforced concrete structures without significant loss of load-bearing capacity are also highlighted. Options for facilitation of structures are presented in the article by lightening the metal load-bearing elements and reducing the weight of the reinforced concrete slab of the carriageway. Reducing the weight of metal elements can be obtained through the use of perforated elements, which can be performed by waste-free technology. To reduce the cost of materials and reduce the weight of the reinforced concrete slab, it is designed lightweight – hollow or ribbed. When removing concrete from the stretched zone, only the ribs of the width required to accommodate the welded frames and ensure the strength of the panels on an inclined cross section are retained. In this case, the plate in the span between the ribs work on the bend as beams of T-section. The top shelf of the plate also works on the local bend between the ribs. During the inspection, the article presents a new design of reinforced concrete girder structure, using perforated box metal elements, made by waste-free technology, and lightweight reinforced concrete slab of the carriageway with hollow formers. Metal blocks are connected to each other by bolts. Metal blocks are made of perforated sheet elements made of waste-free technology. Each block consists of two main beams, transverse diaphragms and a lower plate. The upper belt of the main beams is implemented with the device of horizontal shelves along the entire length of the beams, performing the function of a supporting element for the reinforced concrete slab. Combining all structural elements into a single finished unit is carried out in the factory by automatic welding, which, in turn, allows us to achieve the high factory readiness. The diaphragms of the block are made with a comb along the upper border, on which a profiled steel sheet is placed, which is a fixed formwork for a reinforced concrete slab. The plate is made of non-removable formwork. To ensure the joint operation of the metal part and the reinforced concrete slab, a system of discrete-continuous connections in the form of rigid stops connected in the longitudinal and transverse directions by reinforcing rods is proposed.

All-position welding control system based on machine vision and nonlinear regression

Aiming at the problems of poor welding quality and low degree of automatic welding on the engineering site, a welding process parameter control method based on machine vision and nonlinear regression technology is proposed. Firstly, a vision unit and a peripheral sensor unit are designed to obtain the information of each influencing factor of the welding process parameters. Secondly, a clustering algorithm is used to improve the extraction accuracy of feature point coordinates of weld images. Thirdly, a nonlinear regression fitting method is proposed to determine the mathematical relationship between welding quality at different welding positions and corresponding process parameters. Experimental results show that the control system is easy to operate, and the flexible control of welding process parameters in the whole process is realized. The weld cumulative height and width deviations are less than 0.5 and 0.3 mm, respectively. The welding surface is stable and meets welding requirements. Therefore, this method is of great practical significance in engineering field welding.