Dmitrii A. Shatagin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Dmitrii A. Shatagin has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Yuri G. Kabaldin
Alekseev Nizhny Novgorod State Technical University, Nizhny Novgorod, Russia
10 shared publications - Maksim S. Anosov
R.E. Alekseev Nizhny Novgorod State Technical University
7 shared publications - Yuri G. Kabaldin
R.E. Alekseev Nizhny Novgorod State Technical University
5 shared publications A. A. Golovin
Alekseev Nizhny Novgorod State Technical University
4 shared publicationsM. S. Anosov
Alekseev Nizhny Novgorod State Technical University
4 shared publicationsP. V. Kolchin
4 shared publications
Latest Publications
- 30 September 2026
- Published by Nosov Magnitogorsk State Technical University in Vestnik of Nosov Magnitogorsk State Technical University
- Vol. 24 (3)
DEVELOPMENT OF AN INTEGRATED APPROACH TO THE DIAGNOSTICS OF WELDING AND WIRE ARC ADDITIVE MANUFACTURING PROCESSES
The paper addresses the pressing issue of ensuring the stability and quality of the wire arc additive manufacturing (WAAM) process, which limits its widespread implementation in critical manufacturing applications. Conventional non-destructive testing methods, applied after the completion of the process, do not allow timely process adjustment. Objectives. The study is aimed at developing an integrated diagnostic approach based on in-situ monitoring for predictive process control. For this purpose, a method for synchronous multiparametric recording of key physical fields has been proposed, including electrical arc characteristics (voltage and current) and acoustic emission (AE) signals. During the experimental studies, wall-shaped specimens have been deposited while the corresponding data have been recorded simultaneously. The analysis has included the construction of spectrograms and phase portraits (energy-acoustic attractors), as well as the evaluation of their fractal dimensions to identify indicators of process stability and defect formation. Originality. The novelty of the study lies in the integration of multiparametric data and the application of deep neural network models for real-time data analysis. A comparative analysis of various architectures, including convolutional and recurrent neural networks, has been performed to classify process states based on raw and processed signals. The best result, with an accuracy of 91%, has been achieved by a bidirectional recurrent neural network (BiLSTM) using pre-calculated nonlinear signal parameters (fractal dimension and spectral entropy) as key features. This enables the model to effectively identify subtle patterns preceding the loss of process stability. Practical Relevance. The study provides a basis for an intelligent predictive control system capable of forecasting process instability within fractions of a second. This paves the way for closed-loop adaptive control systems, which are critical for the industrial implementation of WAAM, enabling both quality control and real-time optimization of process parameters. Further development will involve integrating the trained model into the process control system and validat-ing the proposed approach across a wider range of materials and deposition parameters.
- 30 September 2026
- Published by Nosov Magnitogorsk State Technical University in Vestnik of Nosov Magnitogorsk State Technical University
- Vol. 24 (3)
DEVELOPMENT OF AN INTEGRATED APPROACH TO THE DIAGNOSTICS OF WELDING AND WIRE ARC ADDITIVE MANUFACTURING PROCESSES
The paper addresses the pressing issue of ensuring the stability and quality of the wire arc additive manufacturing (WAAM) process, which limits its widespread implementation in critical manufacturing applications. Conventional non-destructive testing methods, applied after the completion of the process, do not allow timely process adjustment. Objectives. The study is aimed at developing an integrated diagnostic approach based on in-situ monitoring for predictive process control. For this purpose, a method for synchronous multiparametric recording of key physical fields has been proposed, including electrical arc characteristics (voltage and current) and acoustic emission (AE) signals. During the experimental studies, wall-shaped specimens have been deposited while the corresponding data have been recorded simultaneously. The analysis has included the construction of spectrograms and phase portraits (energy-acoustic attractors), as well as the evaluation of their fractal dimensions to identify indicators of process stability and defect formation. Originality. The novelty of the study lies in the integration of multiparametric data and the application of deep neural network models for real-time data analysis. A comparative analysis of various architectures, including convolutional and recurrent neural networks, has been performed to classify process states based on raw and processed signals. The best result, with an accuracy of 91%, has been achieved by a bidirectional recurrent neural network (BiLSTM) using pre-calculated nonlinear signal parameters (fractal dimension and spectral entropy) as key features. This enables the model to effectively identify subtle patterns preceding the loss of process stability. Practical Relevance. The study provides a basis for an intelligent predictive control system capable of forecasting process instability within fractions of a second. This paves the way for closed-loop adaptive control systems, which are critical for the industrial implementation of WAAM, enabling both quality control and real-time optimization of process parameters. Further development will involve integrating the trained model into the process control system and validat-ing the proposed approach across a wider range of materials and deposition parameters.
- 1 December 2023
- Published by Pleiades Publishing Ltd in Russian Metallurgy (Metally)
- Vol. 2023 (13) , 2270-2274
Structure Formation in 09G2S Steel Produced by Additive Electric Arc Growth
Currently, additive technologies, in particular, electric arc growth as the most universal and productive, are used to produce individual machine parts. The problem of studying the process of structure formation in alloys during electric arc additive growth to ensure the necessary parameters of the microstructure of a material and its mechanical properties is challenging. 09G2S steel samples for research are fabricated on a developed test bench implementing the technology of 3D printing by electric arc surfacing, microstructural studies on an optical microscope are used, and microhardness measurements are carried out. The features of structure formation in a 09G2S alloy during additive electric arc growth have been determined, and controlled parameters have been identified to ensure the necessary parameters of the structure and, consequently, the mechanical properties of the alloy. The heat input of the surfacing process and the temperature of a thermal cycle are found to play a significant role in the structure formation in the material. The conducted research and established dependences make it possible to control the structural state of 09G2S steel during cladding to ensure the required parameters of its microstructure and mechanical properties.
- 1 December 2023
- Published by Pleiades Publishing Ltd in Russian Metallurgy (Metally)
- Vol. 2023 (13) , 2270-2274
Structure Formation in 09G2S Steel Produced by Additive Electric Arc Growth
Currently, additive technologies, in particular, electric arc growth as the most universal and productive, are used to produce individual machine parts. The problem of studying the process of structure formation in alloys during electric arc additive growth to ensure the necessary parameters of the microstructure of a material and its mechanical properties is challenging. 09G2S steel samples for research are fabricated on a developed test bench implementing the technology of 3D printing by electric arc surfacing, microstructural studies on an optical microscope are used, and microhardness measurements are carried out. The features of structure formation in a 09G2S alloy during additive electric arc growth have been determined, and controlled parameters have been identified to ensure the necessary parameters of the structure and, consequently, the mechanical properties of the alloy. The heat input of the surfacing process and the temperature of a thermal cycle are found to play a significant role in the structure formation in the material. The conducted research and established dependences make it possible to control the structural state of 09G2S steel during cladding to ensure the required parameters of its microstructure and mechanical properties.
- Open Access
- 21 March 2022
- Published by Volga State University of Water Transport in Russian Journal of Water Transport
- No. 70,p. 30-38
Evaluation of the effect of heat treatment on the structure parameters and cold resistance of metals produced by additive electric arc growth
In this work, we studied the influence of the type and mode of heat treatment on the structure and parameters of cold resistance of 09Mn2Si and 07Cr25Ni13 steels obtained by additive electric arc growth. It is shown that, under optimal printing conditions, a relatively uniform and fine-grained material structure is observed in 09Mn2Si steel, while a dendritic structure is observed in the 07Cr25Ni13 alloy. Heat treatment of the investigated alloys leads to a more uniform distribution of structural components in metals, and in steel 07Cr25Ni13 the dendrites are destroyed, which leads to a decrease in the anisotropy of material properties. Also, heat treatment leads to a significant reduction in internal residual stresses in the material. The results of the study of impact strength in a wide range of low temperatures show that in the initial state after surfacing, the investigated alloys have a significant anisotropy of impact strength (up to 8 and 25% for alloy 09Mn2Si and 07Cr25Ni13, respectively). Heat treatment significantly reduces the anisotropy of the properties of the studied alloys and increases the values of impact strength. So for steel 09Mn2Si after heat treatment, an increase in impact strength by more than 1.5 times is observed over the entire temperature range. The studies carried out made it possible to identify the temperature range of the ductile-brittle transition and the impact strength of 09Mn2Si and 07Cr25Ni13 alloys, which is of great practical importance in the manufacture of parts and structural elements of the Northern version.
- 21 March 2022
- Published by Volga State University of Water Transport in Russian Journal of Water Transport
- No. 70,p. 30-38
Open AccessEvaluation of the effect of heat treatment on the structure parameters and cold resistance of metals produced by additive electric arc growth
In this work, we studied the influence of the type and mode of heat treatment on the structure and parameters of cold resistance of 09Mn2Si and 07Cr25Ni13 steels obtained by additive electric arc growth. It is shown that, under optimal printing conditions, a relatively uniform and fine-grained material structure is observed in 09Mn2Si steel, while a dendritic structure is observed in the 07Cr25Ni13 alloy. Heat treatment of the investigated alloys leads to a more uniform distribution of structural components in metals, and in steel 07Cr25Ni13 the dendrites are destroyed, which leads to a decrease in the anisotropy of material properties. Also, heat treatment leads to a significant reduction in internal residual stresses in the material. The results of the study of impact strength in a wide range of low temperatures show that in the initial state after surfacing, the investigated alloys have a significant anisotropy of impact strength (up to 8 and 25% for alloy 09Mn2Si and 07Cr25Ni13, respectively). Heat treatment significantly reduces the anisotropy of the properties of the studied alloys and increases the values of impact strength. So for steel 09Mn2Si after heat treatment, an increase in impact strength by more than 1.5 times is observed over the entire temperature range. The studies carried out made it possible to identify the temperature range of the ductile-brittle transition and the impact strength of 09Mn2Si and 07Cr25Ni13 alloys, which is of great practical importance in the manufacture of parts and structural elements of the Northern version.
- 3 February 2022
- Published by Trans Tech Publications, Ltd. in Materials Science Forum
- Vol. 1052, 407-413
Assessment of Fracture Mechanisms and Temperature of Ductile-Brittle Transition of Metals Obtained on the Basis of 3D Printing Using Neural Network Modeling and Fractal Analysis
In this work, a study of the structure, impact toughness and mechanisms of destruction of steels 08Mn2Si and 07Cr25Ni13 was carried out using optical and electron microscopy. It was found that with a decrease in temperature, the level of impact toughness of the studied steels significantly decreases, so at a temperature of t = -100°C, the impact toughness of 08Mn2Si and 07Cr25Ni13 steel decreases by 83% and 45%, respectively, relative to the temperature t = +20°C. For steel 07Cr25Ni13, in the entire considered range, only the tough component is present in the fracture and there is no temperature of ductile-brittle transition, whereas for steel 08Mn2Si, already at temperatures below t = -41°C (ductile-brittle transition of steel 08Mn2Si), the brittle component begins to dominate and significantly the likelihood of its fragile destruction increases. On the basis of the obtained electronic photographs of the kinks, an artificial neural network (ANN) for the classification of kinks was trained and tested for intermediate test temperatures. When recognizing the viscous component in the fractures of 08Mn2Si steel obtained using the 3D-printing technology by electric arc surfacing, the recognition error does not exceed 7% with the use of ANN.
- 3 February 2022
- Published by Trans Tech Publications, Ltd. in Materials Science Forum
- Vol. 1052, 407-413
Assessment of Fracture Mechanisms and Temperature of Ductile-Brittle Transition of Metals Obtained on the Basis of 3D Printing Using Neural Network Modeling and Fractal Analysis
In this work, a study of the structure, impact toughness and mechanisms of destruction of steels 08Mn2Si and 07Cr25Ni13 was carried out using optical and electron microscopy. It was found that with a decrease in temperature, the level of impact toughness of the studied steels significantly decreases, so at a temperature of t = -100°C, the impact toughness of 08Mn2Si and 07Cr25Ni13 steel decreases by 83% and 45%, respectively, relative to the temperature t = +20°C. For steel 07Cr25Ni13, in the entire considered range, only the tough component is present in the fracture and there is no temperature of ductile-brittle transition, whereas for steel 08Mn2Si, already at temperatures below t = -41°C (ductile-brittle transition of steel 08Mn2Si), the brittle component begins to dominate and significantly the likelihood of its fragile destruction increases. On the basis of the obtained electronic photographs of the kinks, an artificial neural network (ANN) for the classification of kinks was trained and tested for intermediate test temperatures. When recognizing the viscous component in the fractures of 08Mn2Si steel obtained using the 3D-printing technology by electric arc surfacing, the recognition error does not exceed 7% with the use of ANN.
- 3 February 2022
- Published by Trans Tech Publications, Ltd. in Materials Science Forum
- Vol. 1052, 414-419
Optimization of 3D Printing Modes for Electric Arc Surfacing Using a Digital Twin of the Process
The article proposes a method for choosing the optimal modes of 3D printing by electric arc surfacing on CNC machines using a digital twin of the process. As a digital twin, a neural network model is used that approximates the dependence of the stability of the surfacing process and the geometric parameters of the printed layer on the surfacing modes: voltage, current and minute feed. The possibility of optimizing 3D printing modes using neural network modeling based on a modified backpropagation method is shown.
- 3 February 2022
- Published by Trans Tech Publications, Ltd. in Materials Science Forum
- Vol. 1052, 414-419
Optimization of 3D Printing Modes for Electric Arc Surfacing Using a Digital Twin of the Process
The article proposes a method for choosing the optimal modes of 3D printing by electric arc surfacing on CNC machines using a digital twin of the process. As a digital twin, a neural network model is used that approximates the dependence of the stability of the surfacing process and the geometric parameters of the printed layer on the surfacing modes: voltage, current and minute feed. The possibility of optimizing 3D printing modes using neural network modeling based on a modified backpropagation method is shown.
- 17 December 2019
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2188 (1) , 020014
Neuromorphic adaptive control of hybrid processing on CNC machines
The paper considers the possibility of using neuromorphic controllers in adaptive control systems of cyber- physical hybrid processing systems, including 3D printing and subsequent mechanical processing. The application of the Big Data and machine learning technologies for obtaining “digital twins” of hybrid processing is shown. A hardware implementation of “digital twins” of a cyber-physical system as part of a neuromorphic controller as part of automatic control of technological processes on CNC machines is proposed.
- 17 December 2019
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2188 (1) , 020014
Neuromorphic adaptive control of hybrid processing on CNC machines
The paper considers the possibility of using neuromorphic controllers in adaptive control systems of cyber- physical hybrid processing systems, including 3D printing and subsequent mechanical processing. The application of the Big Data and machine learning technologies for obtaining “digital twins” of hybrid processing is shown. A hardware implementation of “digital twins” of a cyber-physical system as part of a neuromorphic controller as part of automatic control of technological processes on CNC machines is proposed.
- 24 October 2019
- Published by Allerton Press in Russian Engineering Research
- Vol. 39 (10) , 848-851
Digital Twin for 3D Printing on CNC Machines
A system has been developed for 3D printing by means of arc welding in CNC machines. Modules for high-speed computation and for the training of neural networks (with feedback) may be...
- 24 October 2019
- Published by Allerton Press in Russian Engineering Research
- Vol. 39 (10) , 848-851
Digital Twin for 3D Printing on CNC Machines
A system has been developed for 3D printing by means of arc welding in CNC machines. Modules for high-speed computation and for the training of neural networks (with feedback) may be...