Edgar Chávez, Erick Galarza, Jhonatan Lulo, N. Ramos, V. Acosta, Juan Jose Uchuya, Jose Luis Roggero
{"title":"Calculation of the Sankey diagram for ship propulsion plants using online simulators","authors":"Edgar Chávez, Erick Galarza, Jhonatan Lulo, N. Ramos, V. Acosta, Juan Jose Uchuya, Jose Luis Roggero","doi":"10.5957/smc-2021-133","DOIUrl":"https://doi.org/10.5957/smc-2021-133","url":null,"abstract":"In recent years, the shipbuilding industry has been incorporating different technological innovations that adapt innovative techniques such as image correlation for 3D reconstruction, reduced order modeling methods for digital twins, pixel amplification techniques to measure vibrations, among other methodologies. The advancement of these methodologies help to obtain visual resources that allow a better understanding of a given phenomenon, which complements the results found numerically, analytically or experimentally. The present study collects data from different configurations of ship propulsion plants, which are based on real operating conditions. The operating conditions are given for fishing vessels; the \"navigation\" condition is selected as being the most frequent and the \"fishing operation\" as being the most energetically critical. These conditions are attached to the choice of the ship's propeller. For the propeller, the diameter, the number of blades and the length of the drive shaft from the main engine position to the propeller are considered. Three engine power levels (low, medium and high) are selected, represented by 300, 850 and 1300 HP engines. The aforementioned operating conditions are used to calculate the efficiency of the propulsion plant, obtaining several combinations. Furthermore, these configurations are expressed by means of Sankey diagrams and illustrations of the plant configurations in 3D using WebGL and Threejs libraries. Complementarily, these data are observed in an online simulator called \"ShipSim\", using \"html\" coding.","PeriodicalId":243899,"journal":{"name":"Day 3 Fri, October 29, 2021","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123276655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Estimating Ship Underwater Radiated Noise from Onboard Vibrations","authors":"Esen Cintosun, L. Gilroy","doi":"10.5957/smc-2021-114","DOIUrl":"https://doi.org/10.5957/smc-2021-114","url":null,"abstract":"The acoustic signature of an Orca-class training vessel (Patrol Craft Training, PCT) Moose from the Royal Canadian Navy (RCN) was measured at the RCN’s Patricia Bay acoustic range on Vancouver Island, British Columbia, Canada. The acoustic range trials included accelerometer measurements on the ship hull and in the engine room and hydrophone measurements at approximately 100 m from the ship. The trials were carried out at the ship speed range of 3 to 20 knots. The test data from all the trial runs was used to derive, evaluate and validate the method of estimating ship underwater radiated noise from onboard vibrations. In the investigation, the runs were split into two sets: a training set and a testing set. A least squares approximation, AQV (average quadratic velocity) SL (source level) correlation, was then applied to the training set data to formulate a transfer function to estimate the underwater radiated noise from onboard vibrations. The AQV is calculated from accelerometer measurements (vibration levels) and SL is obtained from the hydrophone measurements. The third octave frequency band (from 10 Hz to 10 kHz) SL estimations of the testing set runs (using the transfer function and AQV) are within 1 to 3 dB of SL from the hydrophone measurements. This study demonstrates a capability of monitoring underwater radiated noise from ships using only onboard vibration levels which may be of interest for future projects relating to the reduction of shipping noise against a threshold in acoustically sensitive environments.","PeriodicalId":243899,"journal":{"name":"Day 3 Fri, October 29, 2021","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122293429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Canberk Karahan, Sebnem Helvacioglu, I. H. Helvacioglu
{"title":"Applying Reverse Engineering Principles on Analysis of Failures Occurred in Ship Production","authors":"Canberk Karahan, Sebnem Helvacioglu, I. H. Helvacioglu","doi":"10.5957/smc-2021-109","DOIUrl":"https://doi.org/10.5957/smc-2021-109","url":null,"abstract":"In the current work, a new error evaluation methodology is introduced based on error analysis in ship production with reverse engineering data. The aim is to determine the errors and prevent or reduce the occurrence in other projects. First step is to compose a database of the errors; then, group the similar errors and calculate the Error Priority Number (EPN) by the evaluation of the predetermined criteria. The radar diagrams, which are suitable for representing a number of parameters having the same variables, were used to present the error groups in a simple way. The error groups were created on the diagram with the scores taken from the specific criteria. With the aid of the radar diagram, valuable information is given by presenting similarities and dissimilarities of these errors with other error groups. After examining the radar diagrams and evaluating the results, the cause and effect diagrams were prepared for these error groups from the field experts. Thus, the methodology should be customized for the shipyard to ensure maximum efficiency.","PeriodicalId":243899,"journal":{"name":"Day 3 Fri, October 29, 2021","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130297970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Using AI at the Edge and Incremental Machine Learning to Process Onboard Instrument Data","authors":"N. Parkyn","doi":"10.5957/smc-2021-048","DOIUrl":"https://doi.org/10.5957/smc-2021-048","url":null,"abstract":"Emerging heterogeneous computing, computing at the edge, machine learning and AI at the edge technology drives approaches and techniques for processing and analysing onboard instrument data in near real-time. The author has used edge computing and neural networks combined with high performance heterogeneous computing platforms to accelerate AI workloads. Heterogeneous computing hardware used is readily available, low cost, delivers impressive AI performance and can run multiple neural networks in parallel. Collecting, processing and machine learning from onboard instruments data in near real-time is not a trivial problem due to data volumes, complexities of data filtering, data storage and continual learning. Little research has been done on continual machine learning which aims at a higher level of machine intelligence through providing the artificial agents with the ability to learn from a non-stationary and never-ending stream of data. The author has applied the concept of continual learning to building a system that continually learns from actual boat performance and refines predictions previously done using static VPP data. The neural networks used are initially trained using the output from traditional VPP software and continue to learn from actual data collected under real sailing conditions. The author will present the system design, AI, and edge computing techniques used and the approaches he has researched for incremental training to realise continual learning.","PeriodicalId":243899,"journal":{"name":"Day 3 Fri, October 29, 2021","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129982407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
