Input-Output Selection for LSTM-Based Reduced-Order State Estimator Design

نویسندگان

چکیده

In this work, we propose a sensitivity-based approach to construct reduced-order state estimators based on recurrent neural networks (RNN). It is assumed that mechanistic model available but too computationally complex for estimator design and only some target outputs are of interest should be estimated. A can estimate the sufficient address such problem. We introduce an sensitivity analysis determine how select appropriate inputs data collection data-driven development desired accurately. Specifically, consider long short-term memory (LSTM) network, type RNN, as tool train model. Based it, extended Kalman filter, estimator, designed outputs. Simulations carried out illustrate effectiveness applicability proposed approach.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Generalized trellis-based reduced-state soft-input/soft-output algorithms

A general structure of trellis-based reduced-state soft-input/soft-output (RS-SISO) algorithms for communication systems based on concatenated `nite state machines (FSMs) with large memory is presented. Based on forward and backward reduced-state (RS) recursions, a particular structure for the RSSISO algorithm can be obtained by setting suitable parameters in the general formulation. Two novel ...

متن کامل

A reduced-state soft input soft output algorithm based on state partitioning

SISO (Soft Input Soft Output) algorithms are present in several decoding schemes, particularly in concatenated ones that admit an efficient iterative detection, e.g. turbo codes. In recent years these algorithms have been an interesting research subject, especially for the aspects related to complexity reduction. This paper presents the idea of partitioning the set of original states in a chann...

متن کامل

Design of Reduced Rule Multi Input Single Output Fuzzy Controller

It is a well known fact that the performance of a process controlled by a fuzzy logic controller (FLC) can be improved by increasing the number of rules present in the rule base. The rules can be increased either by increasing the number of inputs or by increasing the linguistic variables. In either case with increase in number of rules the computational time and computational memory required i...

متن کامل

Design Input CCITT - SDL Design Output CCITT - SDL Design output Acquiring design rules Design input

The prime goals of this project are (1) developing an automatic software design system that aims at reproducing human cognitive processes; (2) automating software design by shifting the prototyping and modi cations to higher design levels rather than source code. This paper introduces an improved version of the experimental expert system CREATOR2/3 for automatic design of switching software. Ba...

متن کامل

Input and Output Feature Selection

Feature selection is called wrapper whenever the classification algorithm is used in the selection procedure. Our approach makes use of linear classifiers wrapped into a genetic algorithm. As a proof of concept we check its performance against the UCI spam filtering problem showing that the wrapping of linear neural networks is the best. However, making sense of data involves not only selecting...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Mathematics

سال: 2023

ISSN: ['2227-7390']

DOI: https://doi.org/10.3390/math11020400