{"title":"利用递归神经网络算法在全球定位系统中断时应用动态传递对准方法","authors":"Alireza Sharifi , Ali Baniasad , Saeid Mozafari","doi":"10.1016/j.engappai.2025.111167","DOIUrl":null,"url":null,"abstract":"<div><div>In this study, a Robust in-motion Transfer Alignment method based on the multilayer Neural Network, called RTA-NN, is proposed to correct the initial information of the slave vehicle based on the Strapdown Inertial Navigation System (SINS) and Global Positioning System (GPS) integrated navigation structure of the master vehicle, when the GPS data of the master vehicle is not available. For this purpose, first, the SINS equations of the master vehicle are extracted based on the low-grade Inertial Measurement Units (IMU) to compute the position, velocity, and attitude of the master vehicle. Then, a closed loop Kalman Filter structure is utilized to estimate the true states of the master vehicle in the presence of the GPS receiver. Next, a deep neural network, including multilayer Long-Short Term Memory (LSTM) and multilayer perceptron, is utilized to build the velocity model for the master vehicle based on the current and past samples of the master’s IMU and the SINS outputs. Finally, the performance of the proposed approach is evaluated on the navigation units of the Unmanned Surface Vehicle (USV), considered as master, and Remotely Operated Vehicle (ROV), considered as slave. The results demonstrate the effectiveness of the proposed transfer alignment approach based on the neural network, when the GPS signals are disrupted. During 100-second GPS outages, the proposed method reduces navigation errors by 0.1%, demonstrating the robustness and accuracy of the RTA-NN approach in maintaining reliable transfer alignment without GPS.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"157 ","pages":"Article 111167"},"PeriodicalIF":8.0000,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Applied an in-motion transfer alignment approach during global positioning system outages utilizing a recurrent neural network algorithm\",\"authors\":\"Alireza Sharifi , Ali Baniasad , Saeid Mozafari\",\"doi\":\"10.1016/j.engappai.2025.111167\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>In this study, a Robust in-motion Transfer Alignment method based on the multilayer Neural Network, called RTA-NN, is proposed to correct the initial information of the slave vehicle based on the Strapdown Inertial Navigation System (SINS) and Global Positioning System (GPS) integrated navigation structure of the master vehicle, when the GPS data of the master vehicle is not available. For this purpose, first, the SINS equations of the master vehicle are extracted based on the low-grade Inertial Measurement Units (IMU) to compute the position, velocity, and attitude of the master vehicle. Then, a closed loop Kalman Filter structure is utilized to estimate the true states of the master vehicle in the presence of the GPS receiver. Next, a deep neural network, including multilayer Long-Short Term Memory (LSTM) and multilayer perceptron, is utilized to build the velocity model for the master vehicle based on the current and past samples of the master’s IMU and the SINS outputs. Finally, the performance of the proposed approach is evaluated on the navigation units of the Unmanned Surface Vehicle (USV), considered as master, and Remotely Operated Vehicle (ROV), considered as slave. The results demonstrate the effectiveness of the proposed transfer alignment approach based on the neural network, when the GPS signals are disrupted. During 100-second GPS outages, the proposed method reduces navigation errors by 0.1%, demonstrating the robustness and accuracy of the RTA-NN approach in maintaining reliable transfer alignment without GPS.</div></div>\",\"PeriodicalId\":50523,\"journal\":{\"name\":\"Engineering Applications of Artificial Intelligence\",\"volume\":\"157 \",\"pages\":\"Article 111167\"},\"PeriodicalIF\":8.0000,\"publicationDate\":\"2025-06-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Engineering Applications of Artificial Intelligence\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0952197625011686\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AUTOMATION & CONTROL SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Engineering Applications of Artificial Intelligence","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0952197625011686","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}
Applied an in-motion transfer alignment approach during global positioning system outages utilizing a recurrent neural network algorithm
In this study, a Robust in-motion Transfer Alignment method based on the multilayer Neural Network, called RTA-NN, is proposed to correct the initial information of the slave vehicle based on the Strapdown Inertial Navigation System (SINS) and Global Positioning System (GPS) integrated navigation structure of the master vehicle, when the GPS data of the master vehicle is not available. For this purpose, first, the SINS equations of the master vehicle are extracted based on the low-grade Inertial Measurement Units (IMU) to compute the position, velocity, and attitude of the master vehicle. Then, a closed loop Kalman Filter structure is utilized to estimate the true states of the master vehicle in the presence of the GPS receiver. Next, a deep neural network, including multilayer Long-Short Term Memory (LSTM) and multilayer perceptron, is utilized to build the velocity model for the master vehicle based on the current and past samples of the master’s IMU and the SINS outputs. Finally, the performance of the proposed approach is evaluated on the navigation units of the Unmanned Surface Vehicle (USV), considered as master, and Remotely Operated Vehicle (ROV), considered as slave. The results demonstrate the effectiveness of the proposed transfer alignment approach based on the neural network, when the GPS signals are disrupted. During 100-second GPS outages, the proposed method reduces navigation errors by 0.1%, demonstrating the robustness and accuracy of the RTA-NN approach in maintaining reliable transfer alignment without GPS.
期刊介绍:
Artificial Intelligence (AI) is pivotal in driving the fourth industrial revolution, witnessing remarkable advancements across various machine learning methodologies. AI techniques have become indispensable tools for practicing engineers, enabling them to tackle previously insurmountable challenges. Engineering Applications of Artificial Intelligence serves as a global platform for the swift dissemination of research elucidating the practical application of AI methods across all engineering disciplines. Submitted papers are expected to present novel aspects of AI utilized in real-world engineering applications, validated using publicly available datasets to ensure the replicability of research outcomes. Join us in exploring the transformative potential of AI in engineering.