Piotr Lacki
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Piotr Lacki has a total of 65 co-authors. Here are the top co-authors by number of shared publications:
- Janina Adamus
Faculty of Civil Engineering, Częstochowa University of Technology, J.H. Dąbrowskiego 69 Str., 42-201 Częstochowa, Poland
22 shared publications - Anna Derlatka
Politechnika Czestochowska
20 shared publications - Wojciech Więckowski
Faculty of Mechanical Engineering, Czestochowa University of Technology, J.H. Dabrowskiego 69 Str., 42-201 Czestochowa, Poland
15 shared publications - Konrad Adamus
Technical University of Częstochowa
6 shared publications - Maciej Motyka
Department of Materials Forming and Processing, Rzeszów University of Technology, Al. Powstancow Warszawy 8, 35-029 Rzeszow, Poland; Department of Materials Science, Rzeszów University of Technology, ul. Zwirki i Wigury 4, 35-036 Rzeszow, Poland
4 shared publications - Paweł Wieczorek
Częstochowa University of Technology
4 shared publications
Latest Publications
- Open Access
Prediction and Optimization of Load-Bearing Capacity in Resistance Spot Welded Titanium Joints Using Neural Networks and Genetic Algorithms
This study investigates the mechanical performance of resistance spot-welded titanium lap joints made of Grade 1 and Grade 5 alloys. Experimental tests were combined with artificial neural network modeling to predict joint load-bearing capacity based on welding current and welding time. Three models were developed for Grade 1/Grade 1, Grade 1/Grade 5, and Grade 5/Grade 5 joints. The mixed Grade 1/Grade 5 joint achieved the highest predictive accuracy, with an R2 value of 0.9289. Statistical evaluation confirmed high model reliability, with mean relative errors between four and six percent. The most accurate model was optimized using a genetic algorithm. The algorithm identified an optimal parameter set consisting of a welding current of 2.89 kA and a welding time of five pulses. This configuration produced a predicted load-bearing capacity of 3.2 kN, which meets the required threshold of three kilonewtons. Contour maps showed that the optimal point lies near the boundary of the high-strength region and corresponds to the lowest welding current and shortest welding time that still ensure sufficient joint quality. The results demonstrate that combining neural network modeling with evolutionary optimization is an effective approach for designing efficient welding processes for dissimilar titanium joints.
Open AccessPrediction and Optimization of Load-Bearing Capacity in Resistance Spot Welded Titanium Joints Using Neural Networks and Genetic Algorithms
This study investigates the mechanical performance of resistance spot-welded titanium lap joints made of Grade 1 and Grade 5 alloys. Experimental tests were combined with artificial neural network modeling to predict joint load-bearing capacity based on welding current and welding time. Three models were developed for Grade 1/Grade 1, Grade 1/Grade 5, and Grade 5/Grade 5 joints. The mixed Grade 1/Grade 5 joint achieved the highest predictive accuracy, with an R2 value of 0.9289. Statistical evaluation confirmed high model reliability, with mean relative errors between four and six percent. The most accurate model was optimized using a genetic algorithm. The algorithm identified an optimal parameter set consisting of a welding current of 2.89 kA and a welding time of five pulses. This configuration produced a predicted load-bearing capacity of 3.2 kN, which meets the required threshold of three kilonewtons. Contour maps showed that the optimal point lies near the boundary of the high-strength region and corresponds to the lowest welding current and shortest welding time that still ensure sufficient joint quality. The results demonstrate that combining neural network modeling with evolutionary optimization is an effective approach for designing efficient welding processes for dissimilar titanium joints.
- 4 May 2026
- Published by Wydawnictwo Polskiej Izby Inżynierów Budownictwa in Inżynier Budownictwa
- No. 5
Projektowanie belki wspornikowej z wykorzystaniem sztucznej inteligencji
The goal of this work was to develop a system that solves engineering problems using natural language. The example presented in this paper solves the cantilever beam problem. The developed DuNLP system used natural language to generate ADINA code using the language generation model. Some parameters (such as the beam’s material properties) were used from the internal database. Other parameters (including the beam’s cross-sectional shape) required training of the AI. Specifically, the training aimed to teach the AI the basic ADINA code commands. DuNLP enables people without specialised engineering or numerical knowledge to solve engineering problems and reduce the required programming skills. DuNLP is a concept that can be used to solve various structural engineering problems, leveraging a wide range of software that processes text files containing command lists.
- 4 May 2026
- Published by Wydawnictwo Polskiej Izby Inżynierów Budownictwa in Inżynier Budownictwa
- No. 5
Projektowanie belki wspornikowej z wykorzystaniem sztucznej inteligencji
The goal of this work was to develop a system that solves engineering problems using natural language. The example presented in this paper solves the cantilever beam problem. The developed DuNLP system used natural language to generate ADINA code using the language generation model. Some parameters (such as the beam’s material properties) were used from the internal database. Other parameters (including the beam’s cross-sectional shape) required training of the AI. Specifically, the training aimed to teach the AI the basic ADINA code commands. DuNLP enables people without specialised engineering or numerical knowledge to solve engineering problems and reduce the required programming skills. DuNLP is a concept that can be used to solve various structural engineering problems, leveraging a wide range of software that processes text files containing command lists.
- Open Access
Artificial Intelligence in Materials Science and Engineering
The collection of 20 scientific articles published within the Special Issue titled “Artificial Intelligence in Materials Science and Engineering” provides a comprehensive overview of contemporary materials engineering, where traditional research methods are increasingly bolstered by advanced digital tools
Open AccessArtificial Intelligence in Materials Science and Engineering
The collection of 20 scientific articles published within the Special Issue titled “Artificial Intelligence in Materials Science and Engineering” provides a comprehensive overview of contemporary materials engineering, where traditional research methods are increasingly bolstered by advanced digital tools
- 17 March 2026
- Published by Springer Nature in Archives of Civil and Mechanical Engineering
- Vol. 26 (3) , 106
Modelling and experimental validation of resistance welded joints in aluminium alloy structures
- 17 March 2026
- Published by Springer Nature in Archives of Civil and Mechanical Engineering
- Vol. 26 (3) , 106
Modelling and experimental validation of resistance welded joints in aluminium alloy structures
- Open Access
- 1 January 2026
- Published by AGH University Press in Computer Methods in Materials Science
- Vol. 26 (1) , 5-22
A Digital Twin for temperature prediction in the laser hardening process of NC10 steel
In this study, Artificial Neural Networks (ANN) were created to develop a Digital Twin (DT) for temperature prediction in the laser hardening process of NC10 steel. The ANN were trained to predict temperature on the top layer during the laser hardening process of NC10 steel samples with different thicknesses and with various laser power and laser scanning speeds. The prediction developed during the project work was based on a parametric numerical model of the laser hardening process for a sample of NC 10 steel, using the Finite Element Method (FEM) within the ADINA software. Numerical simulations enabled a detailed analysis of the temperature produced on the surface of each sample, as well as a visualization of the structural changes made to the sample according to the laser hardening process. It is crucial to create data that reflects reality as closely as possible to assess the best setting for each process. A well created DT allows to make automatically important changes along laser hardening process. To obtain a set of the most efficient parameters for the desired result, Genetic Algorithms (GA) were integrated with the developed ANN. As a result, the authors developed an effective and efficient tool to predict the temperature produced along the laser hardening process.
- 1 January 2026
- Published by AGH University Press in Computer Methods in Materials Science
- Vol. 26 (1) , 5-22
Open AccessA Digital Twin for temperature prediction in the laser hardening process of NC10 steel
In this study, Artificial Neural Networks (ANN) were created to develop a Digital Twin (DT) for temperature prediction in the laser hardening process of NC10 steel. The ANN were trained to predict temperature on the top layer during the laser hardening process of NC10 steel samples with different thicknesses and with various laser power and laser scanning speeds. The prediction developed during the project work was based on a parametric numerical model of the laser hardening process for a sample of NC 10 steel, using the Finite Element Method (FEM) within the ADINA software. Numerical simulations enabled a detailed analysis of the temperature produced on the surface of each sample, as well as a visualization of the structural changes made to the sample according to the laser hardening process. It is crucial to create data that reflects reality as closely as possible to assess the best setting for each process. A well created DT allows to make automatically important changes along laser hardening process. To obtain a set of the most efficient parameters for the desired result, Genetic Algorithms (GA) were integrated with the developed ANN. As a result, the authors developed an effective and efficient tool to predict the temperature produced along the laser hardening process.
- Open Access
- 22 September 2025
- Published by Polish Academy of Sciences Chancellery in Archives of Civil Engineering
- p. 523
Numerical investigation of steel-timber composite beams with cold-formed omega girders, part 1: non-modified beams
This paper presents a preliminary evaluation of the load-bearing capacity of steel-timber composite beams with cold-formed omega girders and laminated veneer lumber slabs. These structural elements may be used as ceiling beams. The finite element models of the analysed composite beams were created in ADINA and Abaqus. The theoretical estimations of the resistance to bending were based on the elastic analysis (elastic resistance to bending) and the rigid-plastic theory (plastic resistance to bending). The elastic load-bearing capacity obtained in the numerical simulation in ADINA was identical to the one from the theoretical analysis. The elastic load-bearing capacity from the numerical analysis in Abaqus was 1.02 times higher than the one from the theoretical analysis. The plastic bending resistance obtained from the theoretical analysis was 1.08 times higher than the one from the numerical simulation in ADINA and 1.03 times higher than the one from the numerical simulation in Abaqus. In part 2 of the paper, a modification to the cross-section and a reinforcing method were proposed.
- 22 September 2025
- Published by Polish Academy of Sciences Chancellery in Archives of Civil Engineering
- p. 523
Open AccessNumerical investigation of steel-timber composite beams with cold-formed omega girders, part 1: non-modified beams
This paper presents a preliminary evaluation of the load-bearing capacity of steel-timber composite beams with cold-formed omega girders and laminated veneer lumber slabs. These structural elements may be used as ceiling beams. The finite element models of the analysed composite beams were created in ADINA and Abaqus. The theoretical estimations of the resistance to bending were based on the elastic analysis (elastic resistance to bending) and the rigid-plastic theory (plastic resistance to bending). The elastic load-bearing capacity obtained in the numerical simulation in ADINA was identical to the one from the theoretical analysis. The elastic load-bearing capacity from the numerical analysis in Abaqus was 1.02 times higher than the one from the theoretical analysis. The plastic bending resistance obtained from the theoretical analysis was 1.08 times higher than the one from the numerical simulation in ADINA and 1.03 times higher than the one from the numerical simulation in Abaqus. In part 2 of the paper, a modification to the cross-section and a reinforcing method were proposed.
- Open Access
- 3 September 2025
- Published by Polish Academy of Sciences Chancellery in Archives of Civil Engineering
- p. 515
Numerical investigation of steel-timber composite beams with cold-formed omega girders. Part 2: Beams with modifications and reinforced beams
This paper is part 2 of a numerical investigation of steel-timber composite beams with cold-formed omega girders and laminated veneer lumber slabs. After conducting a preliminary analysis of the composite beam cross-section in part 1 of the paper, a modification to the cross-section and a reinforcing method were proposed in part 2. In order to increase the load-bearing capacity of the beam, modifications, such as placing a metal sheet inside of the girder or placing a channel outside of the girder, were proposed. These modifications can be made at the production stage of the steel girders. The modification in form of a channel placed outside the omega girder provided the highest increase in the load-bearing capacity. However, the mass of the modified beam with the channel was 29.6% greater than the mass of the reference beam, and the modifying the girder using channels poses a particular challenge. For this reason, the modifications in the form of a flat sheet can be used instead of the channel. The sheet metal may be located inside the omega section to increase the aesthetics of the beam. Furthermore, the effectiveness of the carbon fibre reinforced polymer tape was analysed as a method of beam reinforcement at the building operation stage. The use of the tape resulted in increased load-bearing capacity. However, the increase in the load-bearing capacity of the beam may be limited because of the yielding of the support zone.
- 3 September 2025
- Published by Polish Academy of Sciences Chancellery in Archives of Civil Engineering
- p. 515
Open AccessNumerical investigation of steel-timber composite beams with cold-formed omega girders. Part 2: Beams with modifications and reinforced beams
This paper is part 2 of a numerical investigation of steel-timber composite beams with cold-formed omega girders and laminated veneer lumber slabs. After conducting a preliminary analysis of the composite beam cross-section in part 1 of the paper, a modification to the cross-section and a reinforcing method were proposed in part 2. In order to increase the load-bearing capacity of the beam, modifications, such as placing a metal sheet inside of the girder or placing a channel outside of the girder, were proposed. These modifications can be made at the production stage of the steel girders. The modification in form of a channel placed outside the omega girder provided the highest increase in the load-bearing capacity. However, the mass of the modified beam with the channel was 29.6% greater than the mass of the reference beam, and the modifying the girder using channels poses a particular challenge. For this reason, the modifications in the form of a flat sheet can be used instead of the channel. The sheet metal may be located inside the omega section to increase the aesthetics of the beam. Furthermore, the effectiveness of the carbon fibre reinforced polymer tape was analysed as a method of beam reinforcement at the building operation stage. The use of the tape resulted in increased load-bearing capacity. However, the increase in the load-bearing capacity of the beam may be limited because of the yielding of the support zone.
- Open Access
Optimization of Rotary Friction Welding Parameters Through AI-Augmented Digital Twin Systems
In this study, Artificial Neural Networks (ANN) were employed to develop a Digital Twin (DT) of the Rotary Friction Welding (RFW) process. The neural network models were trained to predict the peak temperature generated during the welding process of dissimilar Ti Grade 2/AA 5005 joints over a temperature range of 20–640 °C. This prediction was based on a parametric numerical model of the RFW process constructed using the Finite Element Method (FEM) within the ADINA System software. Numerical simulations enabled a detailed analysis of the temperature distribution within the weldment. Accurate temperature predictions are essential for assessing the mechanical properties and microstructural integrity of the welded materials. Artificial Intelligence (AI) models, trained on historical data and real-time inputs, dynamically adjust critical process parameters—such as rotational speed, axial force, and friction time—to maintain optimal weld quality. A key advantage of employing AI-augmented DT systems in the RFW process is the ability to conduct real-time (less than 0.1 s) optimization and adaptive control. By integrating a Genetic Algorithm (GA) with the DT algorithm of the RFW process, the authors developed an effective tool for analyzing parameters such as axial force and rotational speed, in order to determine the optimal welding conditions, which translates into improved joint quality, minimized defects, and maximized process efficiency.
Open AccessOptimization of Rotary Friction Welding Parameters Through AI-Augmented Digital Twin Systems
In this study, Artificial Neural Networks (ANN) were employed to develop a Digital Twin (DT) of the Rotary Friction Welding (RFW) process. The neural network models were trained to predict the peak temperature generated during the welding process of dissimilar Ti Grade 2/AA 5005 joints over a temperature range of 20–640 °C. This prediction was based on a parametric numerical model of the RFW process constructed using the Finite Element Method (FEM) within the ADINA System software. Numerical simulations enabled a detailed analysis of the temperature distribution within the weldment. Accurate temperature predictions are essential for assessing the mechanical properties and microstructural integrity of the welded materials. Artificial Intelligence (AI) models, trained on historical data and real-time inputs, dynamically adjust critical process parameters—such as rotational speed, axial force, and friction time—to maintain optimal weld quality. A key advantage of employing AI-augmented DT systems in the RFW process is the ability to conduct real-time (less than 0.1 s) optimization and adaptive control. By integrating a Genetic Algorithm (GA) with the DT algorithm of the RFW process, the authors developed an effective tool for analyzing parameters such as axial force and rotational speed, in order to determine the optimal welding conditions, which translates into improved joint quality, minimized defects, and maximized process efficiency.
- Open Access
- 27 March 2025
- Published by MDPI AG in Preprints.org
Optimization of Rotary Friction Welding Parameters Through AI-Augmented Digital Twin Systems
In this study, Artificial Neural Networks (ANN) were employed to develop a Digital Twin (DT) of the Rotary Friction Welding (RFW) process. The neural network models were trained to predict the peak temperature generated during the welding process of dissimilar Ti Grade 2/AA 5005 joints. This prediction was based on a parametric numerical model of the RFW process constructed using the Finite Element Method (FEM) within the ADINA System software. Numerical simulations enabled a detailed analysis of the temperature distribution within the weldment. Accurate temperature predictions are essential for assessing the mechanical properties and microstructural integrity of the welded materials. Artificial Intelligence (AI) models, trained on historical data and real-time inputs, dynamically adjust critical process parameters—such as rotational speed, axial force, and friction time—to maintain optimal weld quality. A key advantage of employing AI-augmented DT systems in the RFW process is the ability to conduct real-time optimization and adaptive control. By integrating a Genetic Algorithm (GA) with a DT of the RFW process, the authors have developed an effective tool for analyzing a wide range of parameters to identify optimal welding conditions to improve joint quality, minimize defects, and maximize process efficiency.
- 27 March 2025
- Published by MDPI AG in Preprints.org
Open AccessOptimization of Rotary Friction Welding Parameters Through AI-Augmented Digital Twin Systems
In this study, Artificial Neural Networks (ANN) were employed to develop a Digital Twin (DT) of the Rotary Friction Welding (RFW) process. The neural network models were trained to predict the peak temperature generated during the welding process of dissimilar Ti Grade 2/AA 5005 joints. This prediction was based on a parametric numerical model of the RFW process constructed using the Finite Element Method (FEM) within the ADINA System software. Numerical simulations enabled a detailed analysis of the temperature distribution within the weldment. Accurate temperature predictions are essential for assessing the mechanical properties and microstructural integrity of the welded materials. Artificial Intelligence (AI) models, trained on historical data and real-time inputs, dynamically adjust critical process parameters—such as rotational speed, axial force, and friction time—to maintain optimal weld quality. A key advantage of employing AI-augmented DT systems in the RFW process is the ability to conduct real-time optimization and adaptive control. By integrating a Genetic Algorithm (GA) with a DT of the RFW process, the authors have developed an effective tool for analyzing a wide range of parameters to identify optimal welding conditions to improve joint quality, minimize defects, and maximize process efficiency.
- Open Access
- 19 February 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (4) , 2231
The Load-Bearing Capacity Assessment of GFRP Foundation Piles for Transmission Line Poles Using Experimental Tests and Numerical Calculations
This article proposes a novel tube foundation intended for use under transmission line poles. The glass fibre reinforcement polymer (GFRP) piles were driven into sand. A steel tube pole, approximately 6 m high, was mounted on the foundation. The analysed foundations were designed as a monopile to be implemented in the construction of low- and medium-voltage overhead transmission lines. Experimental field tests of innovative piles made of the composite material were carried out on a 1:1 scale. The aim of this work was to develop an isotropic material model treating the GFRP composite as homogeneous. This approach does not fully reproduce the anisotropic behaviour of the composite, but it allows for the engineering design of structures made of the composite material. Laboratory tests in the form of a static tensile test on the samples and a tensile test on the rings cut from a hollow section were performed. The results of the experimental tests and FEM models of the GFRP rings and monopile embedded in sand were compared. The ultimate limit state (ULS) and serviceability limit state (SLS) of the analysed pile were assessed as 14.4 and 9.6 kNm, respectively. The developed numerical model, based on FEM, allows for the load-bearing capacity of the monopile made of GFRP to be reliably determined. From an engineering point of view, the developed numerical model of the GFRP material can be used to calculate the pile load-bearing capacity using engineering software that has limited capabilities in defining material models.
- 19 February 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (4) , 2231
Open AccessThe Load-Bearing Capacity Assessment of GFRP Foundation Piles for Transmission Line Poles Using Experimental Tests and Numerical Calculations
This article proposes a novel tube foundation intended for use under transmission line poles. The glass fibre reinforcement polymer (GFRP) piles were driven into sand. A steel tube pole, approximately 6 m high, was mounted on the foundation. The analysed foundations were designed as a monopile to be implemented in the construction of low- and medium-voltage overhead transmission lines. Experimental field tests of innovative piles made of the composite material were carried out on a 1:1 scale. The aim of this work was to develop an isotropic material model treating the GFRP composite as homogeneous. This approach does not fully reproduce the anisotropic behaviour of the composite, but it allows for the engineering design of structures made of the composite material. Laboratory tests in the form of a static tensile test on the samples and a tensile test on the rings cut from a hollow section were performed. The results of the experimental tests and FEM models of the GFRP rings and monopile embedded in sand were compared. The ultimate limit state (ULS) and serviceability limit state (SLS) of the analysed pile were assessed as 14.4 and 9.6 kNm, respectively. The developed numerical model, based on FEM, allows for the load-bearing capacity of the monopile made of GFRP to be reliably determined. From an engineering point of view, the developed numerical model of the GFRP material can be used to calculate the pile load-bearing capacity using engineering software that has limited capabilities in defining material models.