Abstract Text classification has become a standard component of automated systematic literature review (SLR) solutions, where articles are classified as relevant or irrelevant to a particular literature study topic. Conventional machine learning algorithms for tabular data which can learn quickly from not necessarily large and usually imbalanced data with low computational demands are well suited to this application, but they require that the text data be transformed to a vector representation. This work investigates the utility of different types of text representations for this purpose. Experiments are presented using the bag of words representation and selected representations based on word or text embeddings: word2vec, doc2vec, GloVe, fastText, Flair, and BioBERT. Four classification algorithms are used with these representations: a naive Bayes classifier, logistic regression, support vector machines, and random forest. They are applied to datasets consisting of scientific article abstracts from systematic literature review studies in the medical domain and compared with the pre-trained BioBERT model fine-tuned for classification. The obtained results confirm that the choice of text representation is essential for successful text classification. It turns out that, while the standard bag of words representation is hard to beat, fastText word embeddings make it possible to achieve roughly the same level of classification quality with the added benefit of much lower dimensionality and capability of handling out-of-vocabulary words. More refined embeddings methods based on deep neural networks, while much more demanding computationally, do not appear to offer substantial advantages for the classification task. The fine-tuned BioBERT classification model performs on par with conventional algorithms when they are coupled with their best text representation methods.
{"title":"Bag of Words and Embedding Text Representation Methods for Medical Article Classification","authors":"Paweł Cichosz","doi":"10.34768/amcs-2023-0043","DOIUrl":"https://doi.org/10.34768/amcs-2023-0043","url":null,"abstract":"Abstract Text classification has become a standard component of automated systematic literature review (SLR) solutions, where articles are classified as relevant or irrelevant to a particular literature study topic. Conventional machine learning algorithms for tabular data which can learn quickly from not necessarily large and usually imbalanced data with low computational demands are well suited to this application, but they require that the text data be transformed to a vector representation. This work investigates the utility of different types of text representations for this purpose. Experiments are presented using the bag of words representation and selected representations based on word or text embeddings: word2vec, doc2vec, GloVe, fastText, Flair, and BioBERT. Four classification algorithms are used with these representations: a naive Bayes classifier, logistic regression, support vector machines, and random forest. They are applied to datasets consisting of scientific article abstracts from systematic literature review studies in the medical domain and compared with the pre-trained BioBERT model fine-tuned for classification. The obtained results confirm that the choice of text representation is essential for successful text classification. It turns out that, while the standard bag of words representation is hard to beat, fastText word embeddings make it possible to achieve roughly the same level of classification quality with the added benefit of much lower dimensionality and capability of handling out-of-vocabulary words. More refined embeddings methods based on deep neural networks, while much more demanding computationally, do not appear to offer substantial advantages for the classification task. The fine-tuned BioBERT classification model performs on par with conventional algorithms when they are coupled with their best text representation methods.","PeriodicalId":50339,"journal":{"name":"International Journal of Applied Mathematics and Computer Science","volume":"112 ","pages":"603 - 621"},"PeriodicalIF":1.9,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139025079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Autonomous coordination of multi-agent systems can improve the reaction and dispatching ability of multiple agents to emergency events. The existing research has mainly focused on the reactions or dispatching in specific scenarios. However, task-level coordination has not received significant attention. This study proposes a framework for autonomous switching of task-level strategies (ASTS), which can automatically switch strategies according to different scenarios in the task execution process. The framework is based on the blackboard system, which takes the form of an instance as an agent and the form of norm(s) as a strategy; it uses events to drive autonomous cooperation among multiple agents. A norm may be triggered when an event occurs. After the triggered norm is executed, it can change the data, state, and event in ASTS. To demonstrate the autonomy and switchability of the proposed framework, we develop a fire emergency reaction dispatch system. This system is applied to emergency scenarios involving fires. Five types of strategies and two control modes are designed for this system. Experiments show that this system can autonomously switch between different strategies and control modes in different scenarios with promising results. Our framework improves the adaptability and flexibility of multiple agents in an open environment and represents a solid step toward switching strategies at the task level.
{"title":"Asts: Autonomous Switching of Task–Level Strategies","authors":"Xianchang Wang, Bingyu Lv, kaiyu Wang, Rui Zhang","doi":"10.34768/amcs-2023-0040","DOIUrl":"https://doi.org/10.34768/amcs-2023-0040","url":null,"abstract":"Abstract Autonomous coordination of multi-agent systems can improve the reaction and dispatching ability of multiple agents to emergency events. The existing research has mainly focused on the reactions or dispatching in specific scenarios. However, task-level coordination has not received significant attention. This study proposes a framework for autonomous switching of task-level strategies (ASTS), which can automatically switch strategies according to different scenarios in the task execution process. The framework is based on the blackboard system, which takes the form of an instance as an agent and the form of norm(s) as a strategy; it uses events to drive autonomous cooperation among multiple agents. A norm may be triggered when an event occurs. After the triggered norm is executed, it can change the data, state, and event in ASTS. To demonstrate the autonomy and switchability of the proposed framework, we develop a fire emergency reaction dispatch system. This system is applied to emergency scenarios involving fires. Five types of strategies and two control modes are designed for this system. Experiments show that this system can autonomously switch between different strategies and control modes in different scenarios with promising results. Our framework improves the adaptability and flexibility of multiple agents in an open environment and represents a solid step toward switching strategies at the task level.","PeriodicalId":50339,"journal":{"name":"International Journal of Applied Mathematics and Computer Science","volume":"14 2","pages":"553 - 568"},"PeriodicalIF":1.9,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139021555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Designing power transmission systems is a complex and often time-consuming problem. In this task, various computational tools make it possible to speed up the process and verify a great many different solutions before the final one is developed. It is widely possible today to conduct computer simulations of the operation of various devices before the first physical prototype is built. The article presents an example of a dynamic model of power transmission systems, which has been developed to support work aimed at designing new and optimizing existing systems of that type, as well as to help diagnose them by designing diagnostic algorithms sensitive to early stages of damage development. The paper also presents sample results of tests conducted with the model, used at the gear design stage. In the presented model, the main goal is to reproduce the phenomena occurring in gears as well as possible, using numerous experiments in this direction featured in the literature. Many already historical models present different ways of modeling, but they often made significant simplifications, required by the limitations of the nature of computational capabilities. Differences also result from the purpose of the models being developed, and the analysis of these different ways of doing things makes it possible to choose the most appropriate approach.
{"title":"A Dynamic Model as a Tool for Design and Optimization of Propulsion Systems of Transport Means","authors":"G. Peruń","doi":"10.34768/amcs-2023-0014","DOIUrl":"https://doi.org/10.34768/amcs-2023-0014","url":null,"abstract":"Abstract Designing power transmission systems is a complex and often time-consuming problem. In this task, various computational tools make it possible to speed up the process and verify a great many different solutions before the final one is developed. It is widely possible today to conduct computer simulations of the operation of various devices before the first physical prototype is built. The article presents an example of a dynamic model of power transmission systems, which has been developed to support work aimed at designing new and optimizing existing systems of that type, as well as to help diagnose them by designing diagnostic algorithms sensitive to early stages of damage development. The paper also presents sample results of tests conducted with the model, used at the gear design stage. In the presented model, the main goal is to reproduce the phenomena occurring in gears as well as possible, using numerous experiments in this direction featured in the literature. Many already historical models present different ways of modeling, but they often made significant simplifications, required by the limitations of the nature of computational capabilities. Differences also result from the purpose of the models being developed, and the analysis of these different ways of doing things makes it possible to choose the most appropriate approach.","PeriodicalId":50339,"journal":{"name":"International Journal of Applied Mathematics and Computer Science","volume":"21 1","pages":"183 - 195"},"PeriodicalIF":1.9,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90927520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Every closed-loop system holds a level of fault tolerance, which could be increased by using a fault tolerant control (FTC) scheme. In this paper, an efficient FTC scheme for a class of nonlinear systems (Euler–Lagrange ones) is proposed, which guarantees high performance and stability in a faulty system. This scheme was designed on the basis of a cascade control structure in which the inner loop is the closed-loop system and the external loop is the FTC, a generalized proportional integral (GPI) observer-based controller, which manages the fault tolerance level increment. An important issue of the proposed scheme is that the GPI observer-based controller jointly estimates disturbances and faults, providing information about the state of health of the system, and then compensates their effect. The scheme is efficient because only the inertia matrix is required for the controller design, it is able to preserve the nominal control law unchanged and can operate properly without explicit information about system faults (fault diagnostic module). Simulation results, on a pendulum model, show the effectiveness of the proposed scheme for tracking control.
{"title":"An Efficient Fault Tolerant Control Scheme for Euler–Lagrange Systems","authors":"I. E. Leal-Leal, E. Alcorta-García","doi":"10.34768/amcs-2023-0017","DOIUrl":"https://doi.org/10.34768/amcs-2023-0017","url":null,"abstract":"Abstract Every closed-loop system holds a level of fault tolerance, which could be increased by using a fault tolerant control (FTC) scheme. In this paper, an efficient FTC scheme for a class of nonlinear systems (Euler–Lagrange ones) is proposed, which guarantees high performance and stability in a faulty system. This scheme was designed on the basis of a cascade control structure in which the inner loop is the closed-loop system and the external loop is the FTC, a generalized proportional integral (GPI) observer-based controller, which manages the fault tolerance level increment. An important issue of the proposed scheme is that the GPI observer-based controller jointly estimates disturbances and faults, providing information about the state of health of the system, and then compensates their effect. The scheme is efficient because only the inertia matrix is required for the controller design, it is able to preserve the nominal control law unchanged and can operate properly without explicit information about system faults (fault diagnostic module). Simulation results, on a pendulum model, show the effectiveness of the proposed scheme for tracking control.","PeriodicalId":50339,"journal":{"name":"International Journal of Applied Mathematics and Computer Science","volume":"6 1","pages":"219 - 228"},"PeriodicalIF":1.9,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73547057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Density-based spatial clustering of applications with noise (DBSCAN) is a commonly known and used algorithm for data clustering. It applies a density-based approach and can produce clusters of any shape. However, it has a drawback—its worst-case computational complexity is O(n2) with regard to the number of data items n. The paper presents GrDBSCAN: a granular modification of DBSCAN with reduced complexity. The proposed GrDBSCAN first granulates data into fuzzy granules and then runs density-based clustering on the resulting granules. The complexity of GrDBSCAN is linear with regard to the input data size and higher only for the number of granules. That number is, however, a parameter of the GrDBSCAN algorithm and is (significantly) lower than that of input data items. This results in shorter clustering time than in the case of DBSCAN. The paper is accompanied by numerical experiments. The implementation of GrDBSCAN is freely available from a public repository.
{"title":"GrDBSCAN: A Granular Density–Based Clustering Algorithm","authors":"Dawid Suchy, Krzysztof Siminski","doi":"10.34768/amcs-2023-0022","DOIUrl":"https://doi.org/10.34768/amcs-2023-0022","url":null,"abstract":"Abstract Density-based spatial clustering of applications with noise (DBSCAN) is a commonly known and used algorithm for data clustering. It applies a density-based approach and can produce clusters of any shape. However, it has a drawback—its worst-case computational complexity is O(n2) with regard to the number of data items n. The paper presents GrDBSCAN: a granular modification of DBSCAN with reduced complexity. The proposed GrDBSCAN first granulates data into fuzzy granules and then runs density-based clustering on the resulting granules. The complexity of GrDBSCAN is linear with regard to the input data size and higher only for the number of granules. That number is, however, a parameter of the GrDBSCAN algorithm and is (significantly) lower than that of input data items. This results in shorter clustering time than in the case of DBSCAN. The paper is accompanied by numerical experiments. The implementation of GrDBSCAN is freely available from a public repository.","PeriodicalId":50339,"journal":{"name":"International Journal of Applied Mathematics and Computer Science","volume":"12 1","pages":"297 - 312"},"PeriodicalIF":1.9,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78082684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract This article presents a synthesis strategy aimed at minimizing the dynamic power consumption of combinational circuits mapped in LUT blocks of FPGAs. The implemented circuits represent the mapping of multi-output functions. Properly selected multi-output functions are described using a new form of the binary decision diagram (BDD), which is an extension of pseudomulti-terminal BDDs (PMTBDDs) in the literature. The essence of limiting power consumption is to include additional parameters during decomposition, such as the switching activity associated with the switching PMTBDD (SWPMTBDD). In addition, we highlight the key importance of circuit optimization methods via non-disjoint decomposition when minimizing power consumption. An algorithm is proposed to assess the effectiveness of decomposition, considering several parameters, such as the number of non-disjoint decompositions as well as that of shared and non-shared bound functions or the switching activity. The results of experiments that demonstrate the effectiveness of the proposed methods are also included.
{"title":"Technology Mapping of Multi–Output Functions Leading to the Reduction of Dynamic Power Consumption in FPGAS","authors":"A. Opara, M. Kubica","doi":"10.34768/amcs-2023-0020","DOIUrl":"https://doi.org/10.34768/amcs-2023-0020","url":null,"abstract":"Abstract This article presents a synthesis strategy aimed at minimizing the dynamic power consumption of combinational circuits mapped in LUT blocks of FPGAs. The implemented circuits represent the mapping of multi-output functions. Properly selected multi-output functions are described using a new form of the binary decision diagram (BDD), which is an extension of pseudomulti-terminal BDDs (PMTBDDs) in the literature. The essence of limiting power consumption is to include additional parameters during decomposition, such as the switching activity associated with the switching PMTBDD (SWPMTBDD). In addition, we highlight the key importance of circuit optimization methods via non-disjoint decomposition when minimizing power consumption. An algorithm is proposed to assess the effectiveness of decomposition, considering several parameters, such as the number of non-disjoint decompositions as well as that of shared and non-shared bound functions or the switching activity. The results of experiments that demonstrate the effectiveness of the proposed methods are also included.","PeriodicalId":50339,"journal":{"name":"International Journal of Applied Mathematics and Computer Science","volume":"109 1","pages":"267 - 284"},"PeriodicalIF":1.9,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89171925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Hybrid propulsion in underwater vehicles is the new idea of combining conventional propulsion systems such as screw propellers with other kinds of propulsion like oscillating biomimetic fins, glider wings or jet thrusters. Each of these propulsion systems has its own benefits and drawbacks, and the goal is to have them complement each other in certain conditions. This paper covers the topic of a dynamic model of the pitch and heave motion of the HUUV (hybrid unmanned underwater vehicle) using screw propellers and biomimetic lateral fins. Firstly, the simulation model of the vehicle performing depth and pitch change is presented. Secondly, the vehicle’s hydrodynamic coefficients obtained from CFD simulations are discussed. Thirdly, the results of the HUUV experimental studies in a swimming pool are presented. Lastly, simulation results are compared with those of the experiment to verify the correctness of the model. The vehicle’s motion in the swimming pool during the experiments was recorded using a submerged camcorder and then analysed using the Tracker software.
{"title":"A Dynamic Submerging Motion Model of the Hybrid–Propelled Unmanned Underwater Vehicle: Simulation and Experimental Verification","authors":"Tomasz Talarczyk","doi":"10.34768/amcs-2023-0016","DOIUrl":"https://doi.org/10.34768/amcs-2023-0016","url":null,"abstract":"Abstract Hybrid propulsion in underwater vehicles is the new idea of combining conventional propulsion systems such as screw propellers with other kinds of propulsion like oscillating biomimetic fins, glider wings or jet thrusters. Each of these propulsion systems has its own benefits and drawbacks, and the goal is to have them complement each other in certain conditions. This paper covers the topic of a dynamic model of the pitch and heave motion of the HUUV (hybrid unmanned underwater vehicle) using screw propellers and biomimetic lateral fins. Firstly, the simulation model of the vehicle performing depth and pitch change is presented. Secondly, the vehicle’s hydrodynamic coefficients obtained from CFD simulations are discussed. Thirdly, the results of the HUUV experimental studies in a swimming pool are presented. Lastly, simulation results are compared with those of the experiment to verify the correctness of the model. The vehicle’s motion in the swimming pool during the experiments was recorded using a submerged camcorder and then analysed using the Tracker software.","PeriodicalId":50339,"journal":{"name":"International Journal of Applied Mathematics and Computer Science","volume":"10 1","pages":"207 - 218"},"PeriodicalIF":1.9,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84153961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Associative memories based on lattice algebra are of great interest in pattern recognition applications due to their excellent storage and recall properties. In this paper, a class of binary associative memory derived from lattice memories is presented, which is based on the definition of new complemented binary operations and threshold unary operations. The new learning method generates memories M and W; the former is robust to additive noise and the latter is robust to subtractive noise. In the recall step, the memories converge in a single step and use the same operation as the learning method. The storage capacity is unlimited, and in autoassociative mode there is perfect recall for the training set. Simulation results suggest that the proposed memories have better performance compared to other models.
{"title":"Binary Associative Memories with Complemented Operations","authors":"Arturo Gamino-Carranza","doi":"10.34768/amcs-2023-0019","DOIUrl":"https://doi.org/10.34768/amcs-2023-0019","url":null,"abstract":"Abstract Associative memories based on lattice algebra are of great interest in pattern recognition applications due to their excellent storage and recall properties. In this paper, a class of binary associative memory derived from lattice memories is presented, which is based on the definition of new complemented binary operations and threshold unary operations. The new learning method generates memories M and W; the former is robust to additive noise and the latter is robust to subtractive noise. In the recall step, the memories converge in a single step and use the same operation as the learning method. The storage capacity is unlimited, and in autoassociative mode there is perfect recall for the training set. Simulation results suggest that the proposed memories have better performance compared to other models.","PeriodicalId":50339,"journal":{"name":"International Journal of Applied Mathematics and Computer Science","volume":"6 1","pages":"249 - 265"},"PeriodicalIF":1.9,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74653419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract The paper presents a method of determining the robustness of solutions of systems of interval linear equations (ILEs). The method can be applied also for the ILE systems for which it has been impossible to find solutions so far or for which solutions in the form of improper intervals have been obtained (which cannot be implemented in practice). The research conducted by the authors has shown that for many problems it is impossible to arrive at ideal solutions that would be fully robust to data uncertainty. However, partially robust solutions can be obtained, and those with the highest robustness can be selected and put into practice. The paper shows that the degree of robustness to the uncertainty of the entire system can be calculated on the basis of the degrees of robustness of individual equations, which greatly simplifies calculations. The presented method is illustrated with a series of examples (also benchmark ones) that facilitate its understanding. It is an extension of the authors’ previously published method for first-order ILEs.
{"title":"A Realistic Tolerant Solution of a System of Interval Linear Equations with the Use of Multidimensional Interval Arithmetic","authors":"A. Piegat, M. Pluciński","doi":"10.34768/amcs-2023-0018","DOIUrl":"https://doi.org/10.34768/amcs-2023-0018","url":null,"abstract":"Abstract The paper presents a method of determining the robustness of solutions of systems of interval linear equations (ILEs). The method can be applied also for the ILE systems for which it has been impossible to find solutions so far or for which solutions in the form of improper intervals have been obtained (which cannot be implemented in practice). The research conducted by the authors has shown that for many problems it is impossible to arrive at ideal solutions that would be fully robust to data uncertainty. However, partially robust solutions can be obtained, and those with the highest robustness can be selected and put into practice. The paper shows that the degree of robustness to the uncertainty of the entire system can be calculated on the basis of the degrees of robustness of individual equations, which greatly simplifies calculations. The presented method is illustrated with a series of examples (also benchmark ones) that facilitate its understanding. It is an extension of the authors’ previously published method for first-order ILEs.","PeriodicalId":50339,"journal":{"name":"International Journal of Applied Mathematics and Computer Science","volume":"19 1","pages":"229 - 247"},"PeriodicalIF":1.9,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78043018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract The proper functioning of the fuel cell system depends on the proper operation of all its subsystems. One of the key subsystems is the oxidant supply system, which is responsible for supplying oxygen for the electrochemical reaction taking place in the cell. It also transports the reaction products, i.e., water, outside the fuel cell stack, and in some cases removes excess heat generated in the stack. Changes in the technical condition of machine individual elements always result in changes in operating or residual parameters; however, it is necessary to select appropriate diagnostic methods to be able to use these changes to assess the machine’s technical condition. This article presents the results of research focused on assessing the possibilities of diagnosing the oxidant supply subsystem, in particular, too low an oxidant flow leading to oxygen starvation and cathode flooding, based on the analysis of the voltage occurring in individual cells of the stack as well as on the basis of vibration and acoustic emission (AE) measurements. The presented results show that the faulty operation of that system can be indicated either through electrical and vibroacoustic/acoustic emission measurements.
{"title":"Multi–Symptom Measurement Based Fault Detection of the PEM Fuel Cell System","authors":"A. Polak, Marcin Kluczyk","doi":"10.34768/amcs-2023-0015","DOIUrl":"https://doi.org/10.34768/amcs-2023-0015","url":null,"abstract":"Abstract The proper functioning of the fuel cell system depends on the proper operation of all its subsystems. One of the key subsystems is the oxidant supply system, which is responsible for supplying oxygen for the electrochemical reaction taking place in the cell. It also transports the reaction products, i.e., water, outside the fuel cell stack, and in some cases removes excess heat generated in the stack. Changes in the technical condition of machine individual elements always result in changes in operating or residual parameters; however, it is necessary to select appropriate diagnostic methods to be able to use these changes to assess the machine’s technical condition. This article presents the results of research focused on assessing the possibilities of diagnosing the oxidant supply subsystem, in particular, too low an oxidant flow leading to oxygen starvation and cathode flooding, based on the analysis of the voltage occurring in individual cells of the stack as well as on the basis of vibration and acoustic emission (AE) measurements. The presented results show that the faulty operation of that system can be indicated either through electrical and vibroacoustic/acoustic emission measurements.","PeriodicalId":50339,"journal":{"name":"International Journal of Applied Mathematics and Computer Science","volume":"57 1","pages":"197 - 205"},"PeriodicalIF":1.9,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91228270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","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：