Название: AI Time Series Control System Modelling
Автор: Chuzo Ninagawa
Издательство: Springer
Год: 2023
Страниц: 243
Язык: английский
Формат: pdf (true), epub
Размер: 44.1 MB

This book describes the practical application of Artificial Intelligence (AI) methods using time series data in system control. This book consistently discusses the application of machine learning to the analysis and modelling of time series data of physical quantities to be controlled in the field of system control. Since dynamic systems are not stable steady states but changing transient states, the changing transient states depend on the state history before the change. In other words, it is essential to predict the change from the present to the future based on the time history of each variable in the target system, and to manipulate the system to achieve the desired change. In short, time series is the key to the application of AI machine learning to system control. This is the philosophy of this book: "time series data" + "AI machine learning" = "new practical control methods".

The Internet of Things (IoT) and Artificial Intelligence (AI) are without a doubt the most important technology topics of the near future. As the world undergoes Digital Transformation (DX), the Internet data collection through IoT is becoming the norm, and an era of massive time series data accumulation is about to begin. Furthermore, modeling technology will no longer be able to keep up with manually in extracting relevant information from the large ocean of time series data. AI modeling will be an inevitable core technology of the DX era. Most image recognition, which is a representative of AI technology, can be said to be static modeling that does not depend on past history, but the time series data accumulated by DX can be said to be dynamic modeling in which the appearance of values changes with past history. Long short-term memory (LSTM), a neural network specialized for time series data, has been attracting attention as a neural network that is good at prediction depending on on the history of time series data, and its tools are now readily available.

In each chapter of this book, a structure is adopted that has never been seen before: a section that presents the basic theory in mathematical form, followed by a section that presents practical applications of the theory. In other words, the emphasis is on showing concrete examples of the application of the basic algorithms in the field of system control immediately after understanding them mathematically. By doing so, the author aimed to take a different approach from mathematical books that develop theories in an abstract manner by deriving pure mathematical formulas and from how-to books that only describe how to input and output data to off-the-shelf tools without describing theories.

This book can give my helps to undergradate or graduate students, institute researchers and senior engineers whose scientific background are engineering, mathematics, physics and other natural sciences.