Vlatko Knežević, Ladislav Stazić, Josip Orović, Z. Pavin
Abstract This paper presents a method of adjusting and designing the maintenance scheme for the high-pressure fuel pumps of a slow-speed two-stroke marine engine, MAN 6S70MC-C. The maintenance database for the marine fuel system was obtained from the planned maintenance software, and covered a period of 11 years. During this period, 29 failures occurred that required corrective actions. Our methodology includes failure mode analysis, risk analysis, reliability calculation and maintenance interval adjustment. Each failure is described using a failure mode analysis, based on a combination of the mode and cause of failure. The objective of this study is to recommend a new preventive maintenance interval based on the exponential reliability results and the analysed maintenance data. The initial maintenance plan for each fuel pump was set to 8,000 running hours, whereas in the modified plan, it is recommended to set this to 4,000 hours. Our results show an increase in the system reliability from 60% to 95% when the new modified maintenance plan is applied. In addition, the results and the recommended initial maintenance schedule are validated based on three similar types of engine with the same fuel pump system. The new maintenance approach can reduce the risk of component failure, which will lead to increased reliability of the fuel pump system and the optimisation of maintenance costs.
{"title":"Optimisation of Reliability and Maintenance Plan of the High-Pressure Fuel Pump System on Marine Engine","authors":"Vlatko Knežević, Ladislav Stazić, Josip Orović, Z. Pavin","doi":"10.2478/pomr-2022-0047","DOIUrl":"https://doi.org/10.2478/pomr-2022-0047","url":null,"abstract":"Abstract This paper presents a method of adjusting and designing the maintenance scheme for the high-pressure fuel pumps of a slow-speed two-stroke marine engine, MAN 6S70MC-C. The maintenance database for the marine fuel system was obtained from the planned maintenance software, and covered a period of 11 years. During this period, 29 failures occurred that required corrective actions. Our methodology includes failure mode analysis, risk analysis, reliability calculation and maintenance interval adjustment. Each failure is described using a failure mode analysis, based on a combination of the mode and cause of failure. The objective of this study is to recommend a new preventive maintenance interval based on the exponential reliability results and the analysed maintenance data. The initial maintenance plan for each fuel pump was set to 8,000 running hours, whereas in the modified plan, it is recommended to set this to 4,000 hours. Our results show an increase in the system reliability from 60% to 95% when the new modified maintenance plan is applied. In addition, the results and the recommended initial maintenance schedule are validated based on three similar types of engine with the same fuel pump system. The new maintenance approach can reduce the risk of component failure, which will lead to increased reliability of the fuel pump system and the optimisation of maintenance costs.","PeriodicalId":49681,"journal":{"name":"Polish Maritime Research","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46316129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract The modelling and simulation of planing craft manoeuvres requires coupled six degrees of freedom (6 DOF) motion equations. A coupled 6 DOF motion equation needs hundreds of manoeuvring hydrodynamic coefficients (MHCs) that are mostly determined using the planar motion mechanism (PMM) test. The number of test runs is too high, unless a kind of simplification is imposed to the motion equations. This study modifies 6 DOF motion equations to 4+2 DOF motion equations in which heave and pitch equations are replaced by dynamic draught and trim (so-called running attitude), respectively. The method is applicable for a manoeuvre that commences in the planing regime and ends in the same regime. On that basis, the PMM test is conducted and the model is restrained in the vertical plane at a certain running attitude, determined by a resistance test. The 4+2 DOF method, together with MHCs from the PMM test, are employed for the simulation of turning manoeuvres of a 25° prismatic planing hull. The results of the simulation indicate that the 4+2 DOF method reasonably predicts the path of the craft during the turning manoeuvre and cuts the number of PMM tests required at the same time. The PMM test results show that MHCs are highly related to forward speed and wetted surfaces. The turning manoeuvre simulation shows that the non-linear terms of MHCs cannot be ignored. The STD/L (Steady Turning Diameter divided by Length of the craft) for a planing craft is very large, compared to ships.
{"title":"Simulation of Turning Manoeuvre of Planing Craft Taking Into Account the Running Attitude Change in a Simplified Manner","authors":"K. Sadati, H. Zeraatgar, A. Moghaddas","doi":"10.2478/pomr-2022-0040","DOIUrl":"https://doi.org/10.2478/pomr-2022-0040","url":null,"abstract":"Abstract The modelling and simulation of planing craft manoeuvres requires coupled six degrees of freedom (6 DOF) motion equations. A coupled 6 DOF motion equation needs hundreds of manoeuvring hydrodynamic coefficients (MHCs) that are mostly determined using the planar motion mechanism (PMM) test. The number of test runs is too high, unless a kind of simplification is imposed to the motion equations. This study modifies 6 DOF motion equations to 4+2 DOF motion equations in which heave and pitch equations are replaced by dynamic draught and trim (so-called running attitude), respectively. The method is applicable for a manoeuvre that commences in the planing regime and ends in the same regime. On that basis, the PMM test is conducted and the model is restrained in the vertical plane at a certain running attitude, determined by a resistance test. The 4+2 DOF method, together with MHCs from the PMM test, are employed for the simulation of turning manoeuvres of a 25° prismatic planing hull. The results of the simulation indicate that the 4+2 DOF method reasonably predicts the path of the craft during the turning manoeuvre and cuts the number of PMM tests required at the same time. The PMM test results show that MHCs are highly related to forward speed and wetted surfaces. The turning manoeuvre simulation shows that the non-linear terms of MHCs cannot be ignored. The STD/L (Steady Turning Diameter divided by Length of the craft) for a planing craft is very large, compared to ships.","PeriodicalId":49681,"journal":{"name":"Polish Maritime Research","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47290798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shenglin Zhu, S. Yang, Hui Li, Yan Huang, Zhichang Du, Jianyu Fan, Zhong-hua Lin
Abstract Ocean waves are a promising source of renewable energy, but harvesting this irregular low-frequency energy is challenging due to technological limitations. In this paper, a pendulum plate-based triboelectric nanogenerator (PP-TENG) is proposed. The PP-TENG absorbs wave energy through the pendulum plate installed at the bottom of the device, which generates a swing effect. This drives the motion of the upper TENG power generation unit and generates a charge transfer on the surface of a film of polymer PTFE and nylon, materials which are very sensitive to the low-frequency wave environment. The PP-TENG was tested after building a semi-physical simulation test platform. When the polymer materials were PTFE with a thickness of 0.01 mm and nylon with a thickness of 0.02 mm, 33 commercial LED lamps could be lit simultaneously. Moreover, under short-circuit conditions, the current reached 2.45 μA, and under open-circuit conditions, the voltage reached 212 V. When the PP-TENG was connected in series with a resistor with a resistance of 3 × 105 Ω, its maximum peak power density reached 6.74 mW/m2. It can be concluded that the PP-TENG is characterised by low fabrication costs and excellent energy conversion efficiency. The combination of a pendulum wave energy converter with a TENG shows great output performance. This research lays a solid foundation for practical applications of the proposed structure in the future.
{"title":"A Triboelectric Nanogenerator Based on a Pendulum-Plate Wave Energy Converter","authors":"Shenglin Zhu, S. Yang, Hui Li, Yan Huang, Zhichang Du, Jianyu Fan, Zhong-hua Lin","doi":"10.2478/pomr-2022-0053","DOIUrl":"https://doi.org/10.2478/pomr-2022-0053","url":null,"abstract":"Abstract Ocean waves are a promising source of renewable energy, but harvesting this irregular low-frequency energy is challenging due to technological limitations. In this paper, a pendulum plate-based triboelectric nanogenerator (PP-TENG) is proposed. The PP-TENG absorbs wave energy through the pendulum plate installed at the bottom of the device, which generates a swing effect. This drives the motion of the upper TENG power generation unit and generates a charge transfer on the surface of a film of polymer PTFE and nylon, materials which are very sensitive to the low-frequency wave environment. The PP-TENG was tested after building a semi-physical simulation test platform. When the polymer materials were PTFE with a thickness of 0.01 mm and nylon with a thickness of 0.02 mm, 33 commercial LED lamps could be lit simultaneously. Moreover, under short-circuit conditions, the current reached 2.45 μA, and under open-circuit conditions, the voltage reached 212 V. When the PP-TENG was connected in series with a resistor with a resistance of 3 × 105 Ω, its maximum peak power density reached 6.74 mW/m2. It can be concluded that the PP-TENG is characterised by low fabrication costs and excellent energy conversion efficiency. The combination of a pendulum wave energy converter with a TENG shows great output performance. This research lays a solid foundation for practical applications of the proposed structure in the future.","PeriodicalId":49681,"journal":{"name":"Polish Maritime Research","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69252061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tacjana Niksa-Rynkiewicz, A. Witkowska, J. Głuch, M. Adamowicz
Abstract Very often, the operation of diagnostic systems is related to the evaluation of process functionality, where the diagnostics is carried out using reference models prepared on the basis of the process description in the nominal state. The main goal of the work is to develop a hierarchical gas turbine reference model for the estimation of start-up parameters based on multi-layer perceptron neural networks. A functional decomposition of the gas turbine start-up process was proposed, enabling a modular analysis of selected parameters of the process. Real data sets obtained from observations of the turbo-generator set located on a North Sea platform were used.
{"title":"Monitoring the Gas Turbine Start-Up Phase on a Platform Using a Hierarchical Model Based on Multi-Layer Perceptron Networks","authors":"Tacjana Niksa-Rynkiewicz, A. Witkowska, J. Głuch, M. Adamowicz","doi":"10.2478/pomr-2022-0050","DOIUrl":"https://doi.org/10.2478/pomr-2022-0050","url":null,"abstract":"Abstract Very often, the operation of diagnostic systems is related to the evaluation of process functionality, where the diagnostics is carried out using reference models prepared on the basis of the process description in the nominal state. The main goal of the work is to develop a hierarchical gas turbine reference model for the estimation of start-up parameters based on multi-layer perceptron neural networks. A functional decomposition of the gas turbine start-up process was proposed, enabling a modular analysis of selected parameters of the process. Real data sets obtained from observations of the turbo-generator set located on a North Sea platform were used.","PeriodicalId":49681,"journal":{"name":"Polish Maritime Research","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44045441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract In this study, the impact of propeller emergence on the performance of a ship (speed), propeller (thrust, torque, and RPM), a diesel engine (torque and RPM) and fuel consumption are analysed under severe sea conditions. The goal is to describe the variation in the system variables and fuel consumption rather than analysing the motion of the ship or the phenomenon of propeller ventilation in itself. A mathematical model of the hull, propeller, and engine interactions is developed in which the propeller emergence is included. The system parameters are set using model experiments, empirical formulae, and available data for the engine. The dynamic response of the system is examined in regular head waves under submerged and emerged conditions of the propeller. The pulsatility and the extent of variation of 20 selected variables for the coupled system of hull, propeller, and engine are elaborated using quantitative and qualitative terms and absolute and relative scales. The simulation begins with a ship moving on a straight path, in calm water, with a constant speed for the ship, propeller and engine under steady conditions. The ship then encounters regular head waves with a known time series of the total resistance of the ship in waves. Large motions of the ship create propeller emergence, which in turn reduces the propeller thrust and torque. This study shows that for a specific ship, the mean ship speed, shaft angular velocity, and engine power were slightly reduced in submerged conditions with respect to calm water. We compared the mean values of the variables to those in the emerged condition, and found that the shaft angular velocity was almost the same, the ship speed was considerably reduced, and the engine power significantly dropped with respect to calm water. The ratios of the amplitude of fluctuation to the mean (Amp/Mean) for the ship speed and angular velocity of the shaft under both conditions were considerable, while the Amp/Mean for the power delivered by the engine was extremely high. The outcomes of the study show the degree of influence of propeller emergence on these variables. We identify the extent of each change and categorise the variables into three main groups based on the results.
{"title":"Impact of Propeller Emergence on Hull, Propeller, Engine, and Fuel Consumption Performance in Regular Head Waves","authors":"M. Ghaemi, H. Zeraatgar","doi":"10.2478/pomr-2022-0044","DOIUrl":"https://doi.org/10.2478/pomr-2022-0044","url":null,"abstract":"Abstract In this study, the impact of propeller emergence on the performance of a ship (speed), propeller (thrust, torque, and RPM), a diesel engine (torque and RPM) and fuel consumption are analysed under severe sea conditions. The goal is to describe the variation in the system variables and fuel consumption rather than analysing the motion of the ship or the phenomenon of propeller ventilation in itself. A mathematical model of the hull, propeller, and engine interactions is developed in which the propeller emergence is included. The system parameters are set using model experiments, empirical formulae, and available data for the engine. The dynamic response of the system is examined in regular head waves under submerged and emerged conditions of the propeller. The pulsatility and the extent of variation of 20 selected variables for the coupled system of hull, propeller, and engine are elaborated using quantitative and qualitative terms and absolute and relative scales. The simulation begins with a ship moving on a straight path, in calm water, with a constant speed for the ship, propeller and engine under steady conditions. The ship then encounters regular head waves with a known time series of the total resistance of the ship in waves. Large motions of the ship create propeller emergence, which in turn reduces the propeller thrust and torque. This study shows that for a specific ship, the mean ship speed, shaft angular velocity, and engine power were slightly reduced in submerged conditions with respect to calm water. We compared the mean values of the variables to those in the emerged condition, and found that the shaft angular velocity was almost the same, the ship speed was considerably reduced, and the engine power significantly dropped with respect to calm water. The ratios of the amplitude of fluctuation to the mean (Amp/Mean) for the ship speed and angular velocity of the shaft under both conditions were considerable, while the Amp/Mean for the power delivered by the engine was extremely high. The outcomes of the study show the degree of influence of propeller emergence on these variables. We identify the extent of each change and categorise the variables into three main groups based on the results.","PeriodicalId":49681,"journal":{"name":"Polish Maritime Research","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44397077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract This paper proposes a three degrees of freedom parallel anti-swing method by the main and auxiliary cables to address the problems related to underactuated double-pendulum anti-swing for a ship-mounted jib crane. By analysing the dynamic coupling relationship between the swing of the hook and the payload, it seeks to establish an accurate dynamic model of the anti-swing device under the ship’s rolling and pitching conditions, and discusses the influence of ship excitation, the crane state, load posture and anti-swing parameters on the in-plane and out-of-plane swing angles. The analysis shows that the primary pendulum reduces the in-plane angle by 90% and the out-of-plane angle by 80%, the in-plane angle of the secondary pendulum is reduced by 90%, and the out-of-plane angle is reduced by 80%. The reliability of the simulation data is verified through experiments.
{"title":"Dynamic Analysis and Experiment of Underactuated Double-Pendulum Anti-Swing Device for Ship-Mounted Jib Cranes","authors":"Jianli Wang, Kexin Liu, Shenghai Wang, Haiquan Chen, Yu-qing Sun, Anqi Niu, Haolin Li","doi":"10.2478/pomr-2022-0052","DOIUrl":"https://doi.org/10.2478/pomr-2022-0052","url":null,"abstract":"Abstract This paper proposes a three degrees of freedom parallel anti-swing method by the main and auxiliary cables to address the problems related to underactuated double-pendulum anti-swing for a ship-mounted jib crane. By analysing the dynamic coupling relationship between the swing of the hook and the payload, it seeks to establish an accurate dynamic model of the anti-swing device under the ship’s rolling and pitching conditions, and discusses the influence of ship excitation, the crane state, load posture and anti-swing parameters on the in-plane and out-of-plane swing angles. The analysis shows that the primary pendulum reduces the in-plane angle by 90% and the out-of-plane angle by 80%, the in-plane angle of the secondary pendulum is reduced by 90%, and the out-of-plane angle is reduced by 80%. The reliability of the simulation data is verified through experiments.","PeriodicalId":49681,"journal":{"name":"Polish Maritime Research","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47251268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract There has been a rapidly growing interest in the use of composite and polymer materials for the construction of marine propellers for over 20 years. The main advantages of these materials are a reduction in the weight of the propeller, increased efficiency due to the hydroelasticity effect, a reduction of the hydroacoustic signature, and a cost reduction for serial production. This paper presents an overview of diagnostic methods that can be applied at the design level and during the operation of marine propellers made of polymeric materials. Non-invasive contact and non-contact-based diagnostic techniques for evaluating the technical state of the propeller are reviewed, and the advantages and disadvantages of qualitative and quantitative methods are identified. Operational diagnostic procedures for propellers are areessential for the safety of vessels at sea. Finally, the structure of a diagnostic system is proposed. It combined diagnosis process with the genesis of damage and the prognosis of the technical condition, i.e. production and in-service diagnostics.
{"title":"Design and Operational Diagnostics of Marine Propellers Made of Polymer Materials","authors":"Marcin Kluczyk, A. Grzadziela, Tomislav Batur","doi":"10.2478/pomr-2022-0049","DOIUrl":"https://doi.org/10.2478/pomr-2022-0049","url":null,"abstract":"Abstract There has been a rapidly growing interest in the use of composite and polymer materials for the construction of marine propellers for over 20 years. The main advantages of these materials are a reduction in the weight of the propeller, increased efficiency due to the hydroelasticity effect, a reduction of the hydroacoustic signature, and a cost reduction for serial production. This paper presents an overview of diagnostic methods that can be applied at the design level and during the operation of marine propellers made of polymeric materials. Non-invasive contact and non-contact-based diagnostic techniques for evaluating the technical state of the propeller are reviewed, and the advantages and disadvantages of qualitative and quantitative methods are identified. Operational diagnostic procedures for propellers are areessential for the safety of vessels at sea. Finally, the structure of a diagnostic system is proposed. It combined diagnosis process with the genesis of damage and the prognosis of the technical condition, i.e. production and in-service diagnostics.","PeriodicalId":49681,"journal":{"name":"Polish Maritime Research","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47922131","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Multi-energy hybrid ships are compatible with multiple forms of new energy, and have become one of the most important directions for future developments in this field. A propulsion inverter is an important component of a hybrid DC electrical system, and its reliability has great significance in terms of safe navigation of the ship. A fault diagnosis method based on one-dimensional convolutional neural network (CNN) is proposed that considers the mutual influence between an inverter fault and a limited ship power grid. A tiled voltage reduction method is used for one-to-one correspondence between the inverter output voltage and switching combinations, followed by a combination of a global average pooling layer and a fully connected layer to reduce the model overfitting problem. Finally, fault diagnosis is verified by a Softmax layer with good anti-interference performance and accuracy.
{"title":"A Convolutional Neural Network-Based Method of Inverter Fault Diagnosis in a Ship’s DC Electrical System","authors":"Guo Yan, Yihuai Hu, Q. Shi","doi":"10.2478/pomr-2022-0048","DOIUrl":"https://doi.org/10.2478/pomr-2022-0048","url":null,"abstract":"Abstract Multi-energy hybrid ships are compatible with multiple forms of new energy, and have become one of the most important directions for future developments in this field. A propulsion inverter is an important component of a hybrid DC electrical system, and its reliability has great significance in terms of safe navigation of the ship. A fault diagnosis method based on one-dimensional convolutional neural network (CNN) is proposed that considers the mutual influence between an inverter fault and a limited ship power grid. A tiled voltage reduction method is used for one-to-one correspondence between the inverter output voltage and switching combinations, followed by a combination of a global average pooling layer and a fully connected layer to reduce the model overfitting problem. Finally, fault diagnosis is verified by a Softmax layer with good anti-interference performance and accuracy.","PeriodicalId":49681,"journal":{"name":"Polish Maritime Research","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43730188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract In this article, a deep reinforcement learning based three-dimensional path following control approach is proposed for an underactuated autonomous underwater vehicle (AUV). To be specific, kinematic control laws are employed by using the three-dimensional line-of-sight guidance and dynamic control laws are employed by using the twin delayed deep deterministic policy gradient algorithm (TD3), contributing to the surge velocity, pitch angle and heading angle control of an underactuated AUV. In order to solve the chattering of controllers, the action filter and the punishment function are built respectively, which can make control signals stable. Simulations are carried out to evaluate the performance of the proposed control approach. And results show that the AUV can complete the control mission successfully.
{"title":"Three-Dimensional Path-Following Control of an Autonomous Underwater Vehicle Based on Deep Reinforcement Learning","authors":"Zhenyu Liang, Xingru Qu, Zhao Zhang, Cong Chen","doi":"10.2478/pomr-2022-0042","DOIUrl":"https://doi.org/10.2478/pomr-2022-0042","url":null,"abstract":"Abstract In this article, a deep reinforcement learning based three-dimensional path following control approach is proposed for an underactuated autonomous underwater vehicle (AUV). To be specific, kinematic control laws are employed by using the three-dimensional line-of-sight guidance and dynamic control laws are employed by using the twin delayed deep deterministic policy gradient algorithm (TD3), contributing to the surge velocity, pitch angle and heading angle control of an underactuated AUV. In order to solve the chattering of controllers, the action filter and the punishment function are built respectively, which can make control signals stable. Simulations are carried out to evaluate the performance of the proposed control approach. And results show that the AUV can complete the control mission successfully.","PeriodicalId":49681,"journal":{"name":"Polish Maritime Research","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48146821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Within the frame of CTO’s standard procedure, a propeller open-water test is preceded by a reference measurement, which is taken for a reference propeller model (P356). The results of these measurements are assembled to conduct an open-water test uncertainty analysis. Additional material was gathered from open-water tests that were conducted throughout several research projects on the CP469 model, which is a model of the Nawigator XXI propeller. The latter is a controllable pitch propeller; its pitch was reset before each test repetition. Known procedures for the determination of the open-water test uncertainty do not allow one to extract the manufacture impact directly, without building many models. This factor was addressed with the use of lifting surface calculations. Under certain additional assumptions, these calculations were performed for 100 generic versions of each propeller’s geometry, which were generated by random deviations from the theoretical data within the limits of allowed tolerances. The results of the conducted analyses made it possible to extract separate factors, which were connected to the test’s repeatability, measurement bias and geometry tolerance.
{"title":"Analysis of Model-Scale Open-Water Test Uncertainty","authors":"P. Król","doi":"10.2478/pomr-2022-0039","DOIUrl":"https://doi.org/10.2478/pomr-2022-0039","url":null,"abstract":"Abstract Within the frame of CTO’s standard procedure, a propeller open-water test is preceded by a reference measurement, which is taken for a reference propeller model (P356). The results of these measurements are assembled to conduct an open-water test uncertainty analysis. Additional material was gathered from open-water tests that were conducted throughout several research projects on the CP469 model, which is a model of the Nawigator XXI propeller. The latter is a controllable pitch propeller; its pitch was reset before each test repetition. Known procedures for the determination of the open-water test uncertainty do not allow one to extract the manufacture impact directly, without building many models. This factor was addressed with the use of lifting surface calculations. Under certain additional assumptions, these calculations were performed for 100 generic versions of each propeller’s geometry, which were generated by random deviations from the theoretical data within the limits of allowed tolerances. The results of the conducted analyses made it possible to extract separate factors, which were connected to the test’s repeatability, measurement bias and geometry tolerance.","PeriodicalId":49681,"journal":{"name":"Polish Maritime Research","volume":null,"pages":null},"PeriodicalIF":2.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45515679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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：