Intelligent and Safe Computer Systems in Control and Diagnostics / edited by Zdzislaw Kowalczuk.

Format:

Book

Author/Creator:

Kowalczuk, Zdzisław, author.

Series:

Lecture Notes in Networks and Systems, 2367-3389 ; 545

Language:

English

Subjects (All):

Automatic control.

Computational intelligence.

Control and Systems Theory.

Computational Intelligence.

Local Subjects:

Control and Systems Theory.

Computational Intelligence.

Physical Description:

1 online resource (456 pages)

Edition:

1st ed. 2023.

Place of Publication:

Cham : Springer International Publishing : Imprint: Springer, 2023.

Summary:

The main subject matter of the book is related to the demands of research and industrial centers for diagnostics, monitoring, and decision-making systems that result from the increasing complexity of automation and systems, the need to ensure the highest level of reliability and safety, and continuing research and the development of innovative approaches to fault diagnosis. Most welcome are combinations of domains of engineering knowledge for diagnosis, including detection, isolation, localization, identification, reconfiguration, and fault-tolerant control. This field is open to new challenges, including industrial diagnostics, diagnostics of computer systems and networks, as well as non-industrial applications in the form of medical diagnostics, especially those based on artificial intelligence and deep neural networks. Our community is mainly interested in the following six topics: fault detection, isolation, and identification (FDI); (ii) fault-tolerant control systems; (iii) process safety, quality, and reliability; (iv) medical diagnostics; as well as (v) methodologies based on mathematical modeling, parameter identification and state estimation, qualitative models, statistical and signal processing, artificial intelligence, fuzzy logic and rough sets, expert systems, neural networks; and (vi) industrial applications of diagnostics in fault-tolerant problems, safety, monitoring and alarming, quality control, computer systems and networks, diagnostic software, software reliability, medicine and therapy, environment protection, production control, and other industries such as chemistry, electronics, and power systems. The book is divided into six parts: (I) Artificial Intelligence in Medicine; (II) Cybersecurity; (III) Artificial Neural Networks; (IV) Fault Detection; (V) Systems Modeling; and (VI) Adaptive, Robust and FTC Systems.

Contents:

Intro

Preface

Acknowledgment

Contents

AI in Medicine

Trustworthy Applications of ML Algorithms in Medicine - Discussion and Preliminary Results for a Problem of Small Vessels Disease Diagnosis

1 Introduction

2 Diagnosis of Small Vessel Disease - Fundamentals

3 The Need for Trustworthiness of AI-Based Systems

4 ML-Based System Development

5 Small Vessels Disease Diagnosis - Preliminary Results

6 Concluding Remarks

References

Machine-Aided Detection of SARS-CoV-2 from Complete Blood Count

2 Related Work

3 Our Solution

3.1 Data Collection

3.2 Data Preprocessing

3.3 Architectures

4 Experiments and Results

4.1 Experimental Setup

4.2 Baseline Training on UCC and Zenodo Datasets

4.3 Unbalanced vs Balanced Training

4.4 Impact of Joined Learning with an Additional Dataset

5 Discussion

6 Conclusion

Automatic Breath Analysis System Using Convolutional Neural Networks

2 A Brief Overview of Similar Systems

3 Datasets

4 Breath Analysis System

5 Tests

6 Conclusions

Bridging Functional Model of Arterial Oxygen with Information of Venous Blood Gas: Validating Bioprocess Soft Sensor on Human Respiration

1.1 Historic Context

1.2 Related Work

2 Methods

2.1 Clinical Study Conditions and Hardware

2.2 Model for Partial Pressures of Oxygen and Carbon Dioxide

3 Results

4 Conclusions

COVID-19 Severity Forecast Based on Machine Learning and Complete Blood Count Data

Computer Diagnosis of Color Vision Deficiencies Using a Mobile Device.

1 Classification of Color Vision Deficiencies

2 Computer Test for CVD

3 Solution

4 Conclusion and Future Work

Cybersecurity

Simulation Model and Scenarios for Testing Detectability of Cyberattacks in Industrial Control Systems

2 Description of the Experimental Stand

3 Description of the Simulator

3.1 Overall Structure

3.2 Disturbances, Process and Cyber Faults Simulation

3.3 Possible Hardware in the Loop Configurations

4 Example of Cyber-Attack and Simulation of the System Performance

5 Conclusions

Functional Safety Management in Hazardous Process Installations Regarding the Role of Human Operators Interacting with the Control and Alarm Systems

2 Defining Safety Functions for Reducing Risks

3 Layered Protection System in Hazardous Industrial Plants

4 Incorporating Cognitive Aspects in Human Reliability Analysis

4.1 Human Factors and Systems Cognitive Engineering

4.2 Human Behaviour Types

4.3 Including Cognitive Aspects in Human Reliability Analysis

4.4 Human Reliability Analysis in Context of Accident Scenarios

5 Case Study

5.1 Defining Accident Scenarios in Layered Protection System

5.2 Alarm System Design Issues to Meet Functional Safety Criteria in Context of Human Reliability Analysis

Controller Modelling as a Tool for Cyber-Attacks Detection

2 Cyber-Attack Detection in Control Systems

3 Controller Modelling

3.1 Linear Model

3.2 Neural Network

3.3 Comparison of the Models

4 Case Study

Comparison of Traditional and Elliptic Curves Digital Signatures Providing the Same Security Level

2 Digital Signature Algorithms

2.1 Schemes Based on Discrete Logarithm Complexity.

3 Elliptic Curve Specific Signature Schemes

3.1 ElGamal Digital Signature Based on Elliptic Curves

4 Security Level of Signature Schemes

5 Experimental Comparison of Signature Schemes

5.1 Experiment Setup

5.2 Results

5.3 Results Analysis

Fundamental Concepts of Modeling Computer Security in Cyberphysical Systems

2 Identifying the Attack Surface

2.1 Basic Terminology

2.2 Defining Security Services

3 Modeling Approach

3.1 An Overview

3.2 The NFR Approach

3.3 Simulation Modeling with Monterey Phoenix

3.4 Penetration Testing with Shodan Internet Search Engine

4 Integrating the Simulation and Pentesting into the NFR

4.1 Laboratory SCADA Equipment

4.2 Integration of the Simulation and Pentesting with the NFR

5 Conclusion

Artificial Neural Networks

Training of Deep Learning Models Using Synthetic Datasets

2 Applied Methods and Techniques

2.1 Technical Details

2.2 Collecting 3D Models

2.3 Synthetic Dataset Generation

2.4 Validation Dataset Generation

2.5 Neural Network Architecture

2.6 Transfer Learning via Fine-Tuning

2.7 Scene Parameters Optimization

2.8 Network Parameters and Architecture Optimization

2.9 Validation

3.1 The Role of Scene Organization in the Learning Process

3.2 Impact of Object Texture Properties on the Accuracy of a Neural Network

3.3 Impact of Camera Position on the Accuracy of a Neural Network

3.4 Network Architecture and Hyperparameters Optimization

3.5 PointRend Network

4 Conclusion

Autonomous Perception and Grasp Generation Based on Multiple 3D Sensors and Deep Learning

2.1 Camera Setup

2.2 Camera Calibration

2.3 Point Cloud Merging.

2.4 Converting a Point Cloud to an RGB Image

2.5 Instance Segmentation

2.6 Generating the Robotic Grips

2.7 Grasp Filtration Using GraspFilter

3.1 Point Cloud Merging

3.2 OrthoView

3.3 Instance Segmentation

3.4 Initial-Grasps Generation

3.5 Initial-Grasps Filtration by GraspFilter

4 Discussion

Open-Set Speaker Identification Using Closed-Set Pretrained Embeddings

2 Proposed Approach

2.1 Rationale

2.2 Data Flow

2.3 Speaker Recognition Backbone

3 Embedding-Based Classification of Speakers

4 Results

5 Summary

Condition-Based Monitoring of DC Motors Performed with Autoencoders

2 Related Works

3 Overview

3.1 Autoencoders

4 Experiment Setup

4.1 Hardware and Software

4.2 Application

5 Results

5.1 Parameters

5.2 Datasets

5.3 Single Autoencoder, Single Work Point

5.4 Multiple Autoencoders, Multiple Work Points

5.5 Health Indicator and Signal Correlation

5.6 Comparison with Classical Methods

Estimation of Mass Flow Rates of Two-Phase Flow Using Convolutional Neural Networks

2 Experimental Work

2.1 Experimental Setup

2.2 Methodology

3 Convolutional Neural Networks for Estimation

3.1 Image Classification

3.2 Data Augmentation

3.3 Training, Validation and Testing of the CNN

5 Conclusions a Future Work

Recurrent Neural Network Based Adaptive Variable-Order Fractional PID Controller for Small Modular Reactor Thermal Power Control

2 Problem Statement

2.1 Mathematical Model of SMR Nuclear Reactor

3 Research Method

3.1 Considered Controller Types

3.2 Adaptation Mechanism

4 Simulation Results

Fault Detection.

LSTM Model-Based Fault Detection for Electric Vehicle's Battery Packs

2 Research Methodology

2.1 Liquid Leakage and Liquid Intrusion Detection Method

2.2 Laboratory stand and experiment methodology

3 Results and Discussion

Remaining Useful Life Prediction of the Li-Ion Batteries

2 RUL Prediction Methods

3 Fuzzy Logic Degradation Modeling Framework

4 Battery Remaining Useful Life Prediction

5 Validation of Remaining Useful Life Prediction

6 Conclusion Remarks

Detection of Multiple Leaks in Liquid Transmission Pipelines Using Static Flow Model

2 General Characteristics of Diagnostic Methods

2.1 Method I

2.2 Method II

3 Experimental Data Acquired from the Laboratory Pipeline

3.1 Pipeline Stand

3.2 Conditions of Experiments

4 Results of Verification

4.1 Method I

4.2 Method II

Application of Bayesian Functional Gaussian Mixture Model Classifier for Cable Fault Isolation

2 Bayesian Functional Gaussian Mixture Model

2.1 Spline Representation

2.2 Multiple Levels of Data in Diagnostics

2.3 Class Probability Reconstruction

3 Application to VSC DC Cable Diagnostics

3.1 Computational Setup

3.2 Example of Use

4 Sensitivity Analysis

Verification and Benchmarking in MPA Coprocessor Design Process

3 MPA Coprocessor

4 Design Process

5 Verification and Benchmarking Software

Sensor Fault Analysis of an Isolated Photovoltaic Generator

3 Modeling of the PVG

4 Proposed Diagnostic Approach and Results

4.1 PVG Around the Operating Point

4.2 Generation and Structuring.

4.3 Analysis Through DCS Test.

Notes:

Includes index.

Other Format:

Print version: Kowalczuk, Zdzislaw Intelligent and Safe Computer Systems in Control and Diagnostics

ISBN:

9783031161599

OCLC:

1344159165