Pub Date : 2023-11-06DOI: 10.24425/bpasts.2021.138814
Lingzhi Qu, Junan Yang, Keju Huang, Hui Liu
. Specific emitter identification (SEI) can distinguish single-radio transmitters using the subtle features of the received waveform. Therefore, it is used extensively in both military and civilian fields. However, the traditional identification method requires extensive prior knowledge and is time-consuming. Furthermore, it imposes various effects associated with identifying the communication radiation source signal in complex environments. To solve the problem of the weak robustness of the hand-crafted feature method, many scholars at home and abroad have used deep learning for image identification in the field of radiation source identification. However, the classification method based on a real-numbered neural network cannot extract In-phase/Quadrature (I/Q)-related information from electromagnetic signals. To address these shortcomings, this paper proposes a new SEI framework for deep learning structures. In the proposed framework, a complex-valued residual network structure is first used to mine the relevant information between the in-phase and orthogonal components of the radio frequency baseband signal. Then, a one-dimensional convolution layer is used to a) directly extract the features of a specific one-dimensional time-domain signal sequence, b) use the attention mechanism unit to identify the extracted features, and c) weight them according to their importance. Experiments show that the proposed framework having complex-valued residual networks with attention mechanism has the advantages of high accuracy and superior performance in identifying communication radiation source signals.
{"title":"Specific emitter identification based on one-dimensional complex-valued residual networks with an attention mechanism","authors":"Lingzhi Qu, Junan Yang, Keju Huang, Hui Liu","doi":"10.24425/bpasts.2021.138814","DOIUrl":"https://doi.org/10.24425/bpasts.2021.138814","url":null,"abstract":". Specific emitter identification (SEI) can distinguish single-radio transmitters using the subtle features of the received waveform. Therefore, it is used extensively in both military and civilian fields. However, the traditional identification method requires extensive prior knowledge and is time-consuming. Furthermore, it imposes various effects associated with identifying the communication radiation source signal in complex environments. To solve the problem of the weak robustness of the hand-crafted feature method, many scholars at home and abroad have used deep learning for image identification in the field of radiation source identification. However, the classification method based on a real-numbered neural network cannot extract In-phase/Quadrature (I/Q)-related information from electromagnetic signals. To address these shortcomings, this paper proposes a new SEI framework for deep learning structures. In the proposed framework, a complex-valued residual network structure is first used to mine the relevant information between the in-phase and orthogonal components of the radio frequency baseband signal. Then, a one-dimensional convolution layer is used to a) directly extract the features of a specific one-dimensional time-domain signal sequence, b) use the attention mechanism unit to identify the extracted features, and c) weight them according to their importance. Experiments show that the proposed framework having complex-valued residual networks with attention mechanism has the advantages of high accuracy and superior performance in identifying communication radiation source signals.","PeriodicalId":55299,"journal":{"name":"Bulletin of the Polish Academy of Sciences-Technical Sciences","volume":"11 18","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135584616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-06DOI: 10.24425/bpas.2018.124272
Z. Hajduk
This paper presents the high accuracy hardware implementation of the hyperbolic tangent and sigmoid activation functions for artificial neural networks. A kind of a direct implementation of the functions in a few different versions is proposed and investigated both by software and hardware modeling. A single precision floating point arithmetic is applied. Apart from conventional design style with hardware description language coding, high level synthesis design techniques with the Matlab HDL coder and Xilinx Vivado HLS have also been investigated.
{"title":"Hardware implementation of hyperbolic tangent and sigmoid activation functions","authors":"Z. Hajduk","doi":"10.24425/bpas.2018.124272","DOIUrl":"https://doi.org/10.24425/bpas.2018.124272","url":null,"abstract":"This paper presents the high accuracy hardware implementation of the hyperbolic tangent and sigmoid activation functions for artificial neural networks. A kind of a direct implementation of the functions in a few different versions is proposed and investigated both by software and hardware modeling. A single precision floating point arithmetic is applied. Apart from conventional design style with hardware description language coding, high level synthesis design techniques with the Matlab HDL coder and Xilinx Vivado HLS have also been investigated.","PeriodicalId":55299,"journal":{"name":"Bulletin of the Polish Academy of Sciences-Technical Sciences","volume":"6 22","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135584641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-06DOI: 10.24425/bpasts.2021.138565
Aurel Mihail Titu, Alina Bianca Pop, Marcin Nabiałek, Camelia Cristina Dragomir, Andrei Victor Sandu
. This research presents an experimental study carried out for the modeling and optimization of some technological parameters for the machining of metallic materials. Certain controllable factors were analyzed such as cutting speed, depth of cut, and feed per tooth. A dedicated research methodology was used to obtain a model which subsequently led to a process optimization by performing a required number of experiments utilizing the Minitab software application. The methodology was followed, and the optimal value of the surface roughness was obtained by the milling process for an aluminum alloy type 7136-T76511. A SECO cutting tool was used, which is standard in aluminum machining by milling. Experiments led to defining a cutting regime that was optimal and which shows that the cutting speed has a significant influence on the quality of the machined surface and the depth of cut and feed per tooth has a relatively small impact on the chosen ranges of process parameters.
{"title":"Experimental modeling of the milling process of aluminum alloys used in the aerospace industry","authors":"Aurel Mihail Titu, Alina Bianca Pop, Marcin Nabiałek, Camelia Cristina Dragomir, Andrei Victor Sandu","doi":"10.24425/bpasts.2021.138565","DOIUrl":"https://doi.org/10.24425/bpasts.2021.138565","url":null,"abstract":". This research presents an experimental study carried out for the modeling and optimization of some technological parameters for the machining of metallic materials. Certain controllable factors were analyzed such as cutting speed, depth of cut, and feed per tooth. A dedicated research methodology was used to obtain a model which subsequently led to a process optimization by performing a required number of experiments utilizing the Minitab software application. The methodology was followed, and the optimal value of the surface roughness was obtained by the milling process for an aluminum alloy type 7136-T76511. A SECO cutting tool was used, which is standard in aluminum machining by milling. Experiments led to defining a cutting regime that was optimal and which shows that the cutting speed has a significant influence on the quality of the machined surface and the depth of cut and feed per tooth has a relatively small impact on the chosen ranges of process parameters.","PeriodicalId":55299,"journal":{"name":"Bulletin of the Polish Academy of Sciences-Technical Sciences","volume":"5 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135584650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-06DOI: 10.24425/bpasts.2021.136044
Izabela Rojek, Robert Burduk, Paulina Heda
. The binary classifiers are appropriate for classification problems with two class labels. For multi-class problems, decomposition techniques, like one-vs-one strategy, are used because they allow the use of binary classifiers. The ensemble selection, on the other hand, is one of the most studied topics in multiple classifier systems because a selected subset of base classifiers may perform better than the whole set of base classifiers. Thus, we propose a novel concept of the dynamic ensemble selection based on values of the score function used in the one-vs-one decomposition scheme. The proposed algorithm has been verified on a real dataset regarding the classification of cutting tools. The proposed approach is compared with the static ensemble selection method based on the integration of base classifiers in geometric space, which also uses the one-vs-one decomposition scheme. In addition, other base classification algorithms are used to compare results in the conducted experiments. The obtained results demonstrate the effectiveness of our approach.
{"title":"Ensemble selection in one-versus-one scheme – case study for cutting tools classification","authors":"Izabela Rojek, Robert Burduk, Paulina Heda","doi":"10.24425/bpasts.2021.136044","DOIUrl":"https://doi.org/10.24425/bpasts.2021.136044","url":null,"abstract":". The binary classifiers are appropriate for classification problems with two class labels. For multi-class problems, decomposition techniques, like one-vs-one strategy, are used because they allow the use of binary classifiers. The ensemble selection, on the other hand, is one of the most studied topics in multiple classifier systems because a selected subset of base classifiers may perform better than the whole set of base classifiers. Thus, we propose a novel concept of the dynamic ensemble selection based on values of the score function used in the one-vs-one decomposition scheme. The proposed algorithm has been verified on a real dataset regarding the classification of cutting tools. The proposed approach is compared with the static ensemble selection method based on the integration of base classifiers in geometric space, which also uses the one-vs-one decomposition scheme. In addition, other base classification algorithms are used to compare results in the conducted experiments. The obtained results demonstrate the effectiveness of our approach.","PeriodicalId":55299,"journal":{"name":"Bulletin of the Polish Academy of Sciences-Technical Sciences","volume":"4 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135584653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-06DOI: 10.24425/bpasts.2022.141002
Anna Mackojc, Bogumil Chilinski, Robert Zalewski
. This paper concerns the problem of empirical investigation and mathematical modelling of a novel controllable damper using Vacuum Packed Particles. Vacuum Packed Particles tend to be placed among the group of so-called ‘smart structures’. The macroscopic mechanical features of such structures can be controlled by the partial vacuum parameter. The authors consider an application of Bouc-Wen model in order to represent the dynamic behaviour of the investigated device. The verification of the model response with experimental data is discussed. The Bouc-Wen model parameters identification is described.
{"title":"Preliminary research of a symmetrical controllable granular damper prototype","authors":"Anna Mackojc, Bogumil Chilinski, Robert Zalewski","doi":"10.24425/bpasts.2022.141002","DOIUrl":"https://doi.org/10.24425/bpasts.2022.141002","url":null,"abstract":". This paper concerns the problem of empirical investigation and mathematical modelling of a novel controllable damper using Vacuum Packed Particles. Vacuum Packed Particles tend to be placed among the group of so-called ‘smart structures’. The macroscopic mechanical features of such structures can be controlled by the partial vacuum parameter. The authors consider an application of Bouc-Wen model in order to represent the dynamic behaviour of the investigated device. The verification of the model response with experimental data is discussed. The Bouc-Wen model parameters identification is described.","PeriodicalId":55299,"journal":{"name":"Bulletin of the Polish Academy of Sciences-Technical Sciences","volume":"3 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135584656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-06DOI: 10.24425/bpasts.2019.130191
N. Vasiraja, P. Nagaraj
This article focuses on the finite element analysis (FEA) of the nonlinear behavior of a layered functionally graded material (FGM) plate as concerns displacement, stresses, critical buckling load and fundamental frequency. The material properties of each layer in an FGM plate are assessed according to a ceramic based simple power law distribution and the rules of mixture. The finite element model of a layered FGM plate is developed using ANSYS®15.0 software. The developed finite element model is used to study the static and dynamic responses of an FGM plate. In this paper, the effects of power law distribution, thickness ratio, aspect ratio and boundary conditions are investigated for central displacement, transverse shear stress, transverse normal stress, critical buckling load and fundamental frequency, and the obtained FEA results are in sound agreement with the literature test data results. Since the FGM is used in a high temperature environment, the FE analysis is performed for the FGM plate under a thermal field and then correlated. Finally, the FGM plate is analyzed under a thermomechanical load by using the current FE concept.
{"title":"The effect of material gradient on the static and dynamic response of layered functionally graded material plate using finite element method","authors":"N. Vasiraja, P. Nagaraj","doi":"10.24425/bpasts.2019.130191","DOIUrl":"https://doi.org/10.24425/bpasts.2019.130191","url":null,"abstract":"This article focuses on the finite element analysis (FEA) of the nonlinear behavior of a layered functionally graded material (FGM) plate as concerns displacement, stresses, critical buckling load and fundamental frequency. The material properties of each layer in an FGM plate are assessed according to a ceramic based simple power law distribution and the rules of mixture. The finite element model of a layered FGM plate is developed using ANSYS®15.0 software. The developed finite element model is used to study the static and dynamic responses of an FGM plate. In this paper, the effects of power law distribution, thickness ratio, aspect ratio and boundary conditions are investigated for central displacement, transverse shear stress, transverse normal stress, critical buckling load and fundamental frequency, and the obtained FEA results are in sound agreement with the literature test data results. Since the FGM is used in a high temperature environment, the FE analysis is performed for the FGM plate under a thermal field and then correlated. Finally, the FGM plate is analyzed under a thermomechanical load by using the current FE concept.","PeriodicalId":55299,"journal":{"name":"Bulletin of the Polish Academy of Sciences-Technical Sciences","volume":"2 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135584660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-06DOI: 10.24425/bpasts.2019.130879
M. Siwczyński, S. Żaba
. The article presents an example of the use of functional series for the analysis of nonlinear systems for discrete time signals. The homogeneous operator is defined and it is decomposed into three component operators: the multiplying operator, the convolution operator and the alignment operator. An important case from a practical point of view is considered – a cascade connection of two polynomial systems. A new, binary algorithm for determining the sequence of complex kernels of cascade from two sequences of kernels of component systems is presented. Due to its simplicity, it can be used during iterative processes in the analysis of nonlinear systems (e.g. feedback systems)..
{"title":"The binary algorithm of cascade connection of nonlinear digital filters described in functional series","authors":"M. Siwczyński, S. Żaba","doi":"10.24425/bpasts.2019.130879","DOIUrl":"https://doi.org/10.24425/bpasts.2019.130879","url":null,"abstract":". The article presents an example of the use of functional series for the analysis of nonlinear systems for discrete time signals. The homogeneous operator is defined and it is decomposed into three component operators: the multiplying operator, the convolution operator and the alignment operator. An important case from a practical point of view is considered – a cascade connection of two polynomial systems. A new, binary algorithm for determining the sequence of complex kernels of cascade from two sequences of kernels of component systems is presented. Due to its simplicity, it can be used during iterative processes in the analysis of nonlinear systems (e.g. feedback systems)..","PeriodicalId":55299,"journal":{"name":"Bulletin of the Polish Academy of Sciences-Technical Sciences","volume":"2 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135584661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-06DOI: 10.24425/bpasts.2020.135399
P. Majewski, W.P. Hunek
{"title":"The generalized S- and σ-inverse – a comparative case study for right- and left-invertible plants","authors":"P. Majewski, W.P. Hunek","doi":"10.24425/bpasts.2020.135399","DOIUrl":"https://doi.org/10.24425/bpasts.2020.135399","url":null,"abstract":"","PeriodicalId":55299,"journal":{"name":"Bulletin of the Polish Academy of Sciences-Technical Sciences","volume":"1 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135584668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-06DOI: 10.24425/bpasts.2023.147916
{"title":"147916","authors":"","doi":"10.24425/bpasts.2023.147916","DOIUrl":"https://doi.org/10.24425/bpasts.2023.147916","url":null,"abstract":"","PeriodicalId":55299,"journal":{"name":"Bulletin of the Polish Academy of Sciences-Technical Sciences","volume":"22 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135585651","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-06DOI: 10.24425/bpas.2019.128118
K. Aniserowicz
The paper presents an analysis of overvoltages caused by a direct lightning strike in intrusion detection system equipped with underground radiating cable sensors. Waveforms of currents and voltages in the system components are calculated using analytical formulas basing on a transmission-line model in the frequency domain. The time-domain waveforms are computed using the inverse fast Fourier transform (IFFT). Three network configurations of the intrusion detection system are analyzed.
{"title":"Analytical calculations of surges caused by direct lightning strike to underground intrusion detection system","authors":"K. Aniserowicz","doi":"10.24425/bpas.2019.128118","DOIUrl":"https://doi.org/10.24425/bpas.2019.128118","url":null,"abstract":"The paper presents an analysis of overvoltages caused by a direct lightning strike in intrusion detection system equipped with underground radiating cable sensors. Waveforms of currents and voltages in the system components are calculated using analytical formulas basing on a transmission-line model in the frequency domain. The time-domain waveforms are computed using the inverse fast Fourier transform (IFFT). Three network configurations of the intrusion detection system are analyzed.","PeriodicalId":55299,"journal":{"name":"Bulletin of the Polish Academy of Sciences-Technical Sciences","volume":"372 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135636164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：