Sensors

Research

20 pages, 3061 KiB

Open AccessArticle

Digital Twins in the Practice of High-Energy Physics Experiments: A Gas System for the Multipurpose Detector

by Patryk Chaber, Paweł D. Domański, Daniel Dąbrowski, Maciej Ławryńczuk, Robert Nebeluk, Sebastian Plamowski and Krzysztof Zarzycki

Sensors 2022, 22(2), 678; https://doi.org/10.3390/s22020678 - 16 Jan 2022

Cited by 3 | Viewed by 3191

Abstract

The digital twins technology delivers a new degree of freedom into system implementation and maintenance practice. Using this approach, a technological system can be efficiently modeled and simulated. Furthermore, such a twin offline system can be efficiently used to investigate real system issues [...] Read more.

The digital twins technology delivers a new degree of freedom into system implementation and maintenance practice. Using this approach, a technological system can be efficiently modeled and simulated. Furthermore, such a twin offline system can be efficiently used to investigate real system issues and improvement opportunities, e.g., improvement of the existing control system or development of a new one. This work describes the development of a control system using the digital twins methodology for a gas system delivering a specific mixture of gases to the time-of-flight (ToF) multipurpose detector (MPD) used during high-energy physics experiments in the Joint Institute for Nuclear Research (Dubna, Russia). The gas system digital twin was built using a test stand and further extended into target full-scale installation planned to be built in the near future. Therefore, conducted simulations are used to validate the existing system and to allow validation of the planned new system. Moreover, the gas system digital twin enables testing of new control opportunities, improving the operation of the target gas system. Full article

(This article belongs to the Special Issue Advances in Electronics, Signal Processing and Control Applied in Sensors and Systems)

► Show Figures

Figure 1

18 pages, 1927 KiB

Open AccessArticle

The Use of Drone Photo Material to Classify the Purity of Photovoltaic Panels Based on Statistical Classifiers

by Tomasz Czarnecki and Kacper Bloch

Sensors 2022, 22(2), 483; https://doi.org/10.3390/s22020483 - 9 Jan 2022

Cited by 6 | Viewed by 2245

Abstract

The subject of this work is the analysis of methods of detecting soiling of photovoltaic panels. Environmental and weather conditions affect the efficiency of renewable energy sources. Accumulation of soil, dust, and dirt on the surface of the solar panels reduces the power [...] Read more.

The subject of this work is the analysis of methods of detecting soiling of photovoltaic panels. Environmental and weather conditions affect the efficiency of renewable energy sources. Accumulation of soil, dust, and dirt on the surface of the solar panels reduces the power generated by the panels. This paper presents several variants of the algorithm that uses various statistical classifiers to classify photovoltaic panels in terms of soiling. The base material was high-resolution photos and videos of solar panels and sets dedicated to solar farms. The classifiers were tested and analyzed in their effectiveness in detecting soiling. Based on the study results, a group of optimal classifiers was defined, and the classifier selected that gives the best results for a given problem. The results obtained in this study proved experimentally that the proposed solution provides a high rate of correct detections. The proposed innovative method is cheap and straightforward to implement, and allows use in most photovoltaic installations. Full article

(This article belongs to the Special Issue Advances in Electronics, Signal Processing and Control Applied in Sensors and Systems)

► Show Figures

Figure 1

19 pages, 812 KiB

Open AccessArticle

Multisensor Data Fusion for Localization of Pollution Sources in Wastewater Networks

by Krystian Chachuła, Tomasz Michał Słojewski and Robert Nowak

Sensors 2022, 22(1), 387; https://doi.org/10.3390/s22010387 - 5 Jan 2022

Cited by 5 | Viewed by 2414

Abstract

Illegal discharges of pollutants into sewage networks are a growing problem in large European cities. Such events often require restarting wastewater treatment plants, which cost up to a hundred thousand Euros. A system for localization and quantification of pollutants in utility networks could [...] Read more.

Illegal discharges of pollutants into sewage networks are a growing problem in large European cities. Such events often require restarting wastewater treatment plants, which cost up to a hundred thousand Euros. A system for localization and quantification of pollutants in utility networks could discourage such behavior and indicate a culprit if it happens. We propose an enhanced algorithm for multisensor data fusion for the detection, localization, and quantification of pollutants in wastewater networks. The algorithm processes data from multiple heterogeneous sensors in real-time, producing current estimates of network state and alarms if one or many sensors detect pollutants. Our algorithm models the network as a directed acyclic graph, uses adaptive peak detection, estimates the amount of specific compounds, and tracks the pollutant using a Kalman filter. We performed numerical experiments for several real and artificial sewage networks, and measured the quality of discharge event reconstruction. We report the correctness and performance of our system. We also propose a method to assess the importance of specific sensor locations. The experiments show that the algorithm’s success rate is equal to sensor coverage of the network. Moreover, the median distance between nodes pointed out by the fusion algorithm and nodes where the discharge was introduced equals zero when more than half of the network nodes contain sensors. The system can process around 5000 measurements per second, using 1 MiB of memory per 4600 measurements plus a constant of 97 MiB, and it can process 20 tracks per second, using 1.3 MiB of memory per 100 tracks. Full article

(This article belongs to the Special Issue Advances in Electronics, Signal Processing and Control Applied in Sensors and Systems)

► Show Figures

Figure 1

14 pages, 788 KiB

Open AccessArticle

Attention Autoencoder for Generative Latent Representational Learning in Anomaly Detection

by Ariyo Oluwasanmi, Muhammad Umar Aftab, Edward Baagyere, Zhiguang Qin, Muhammad Ahmad and Manuel Mazzara

Sensors 2022, 22(1), 123; https://doi.org/10.3390/s22010123 - 24 Dec 2021

Cited by 21 | Viewed by 8233

Abstract

Today, accurate and automated abnormality diagnosis and identification have become of paramount importance as they are involved in many critical and life-saving scenarios. To accomplish such frontiers, we propose three artificial intelligence models through the application of deep learning algorithms to analyze and [...] Read more.

Today, accurate and automated abnormality diagnosis and identification have become of paramount importance as they are involved in many critical and life-saving scenarios. To accomplish such frontiers, we propose three artificial intelligence models through the application of deep learning algorithms to analyze and detect anomalies in human heartbeat signals. The three proposed models include an attention autoencoder that maps input data to a lower-dimensional latent representation with maximum feature retention, and a reconstruction decoder with minimum remodeling loss. The autoencoder has an embedded attention module at the bottleneck to learn the salient activations of the encoded distribution. Additionally, a variational autoencoder (VAE) and a long short-term memory (LSTM) network is designed to learn the Gaussian distribution of the generative reconstruction and time-series sequential data analysis. The three proposed models displayed outstanding ability to detect anomalies on the evaluated five thousand electrocardiogram (ECG5000) signals with 99% accuracy and 99.3% precision score in detecting healthy heartbeats from patients with severe congestive heart failure. Full article

(This article belongs to the Special Issue Advances in Electronics, Signal Processing and Control Applied in Sensors and Systems)

► Show Figures

Figure 1

26 pages, 1483 KiB

Open AccessArticle

Generalisation Gap of Keyword Spotters in a Cross-Speaker Low-Resource Scenario

by Łukasz Lepak, Kacper Radzikowski, Robert Nowak and Karol J. Piczak

Sensors 2021, 21(24), 8313; https://doi.org/10.3390/s21248313 - 12 Dec 2021

Cited by 4 | Viewed by 3133

Abstract

Models for keyword spotting in continuous recordings can significantly improve the experience of navigating vast libraries of audio recordings. In this paper, we describe the development of such a keyword spotting system detecting regions of interest in Polish call centre conversations. Unfortunately, in [...] Read more.

Models for keyword spotting in continuous recordings can significantly improve the experience of navigating vast libraries of audio recordings. In this paper, we describe the development of such a keyword spotting system detecting regions of interest in Polish call centre conversations. Unfortunately, in spite of recent advancements in automatic speech recognition systems, human-level transcription accuracy reported on English benchmarks does not reflect the performance achievable in low-resource languages, such as Polish. Therefore, in this work, we shift our focus from complete speech-to-text conversion to acoustic similarity matching in the hope of reducing the demand for data annotation. As our primary approach, we evaluate Siamese and prototypical neural networks trained on several datasets of English and Polish recordings. While we obtain usable results in English, our models’ performance remains unsatisfactory when applied to Polish speech, both after mono- and cross-lingual training. This performance gap shows that generalisation with limited training resources is a significant obstacle for actual deployments in low-resource languages. As a potential countermeasure, we implement a detector using audio embeddings generated with a generic pre-trained model provided by Google. It has a much more favourable profile when applied in a cross-lingual setup to detect Polish audio patterns. Nevertheless, despite these promising results, its performance on out-of-distribution data are still far from stellar. It would indicate that, in spite of the richness of internal representations created by more generic models, such speech embeddings are not entirely malleable to cross-language transfer. Full article

(This article belongs to the Special Issue Advances in Electronics, Signal Processing and Control Applied in Sensors and Systems)

► Show Figures

Figure 1

24 pages, 712 KiB

Open AccessArticle

Control and Diagnostics System Generator for Complex FPGA-Based Measurement Systems

by Wojciech M. Zabołotny, Marek Gumiński, Michał Kruszewski and Walter F.J. Müller

Sensors 2021, 21(21), 7378; https://doi.org/10.3390/s21217378 - 6 Nov 2021

Cited by 1 | Viewed by 3583

Abstract

FPGA-based data acquisition and processing systems play an important role in modern high-speed, multichannel measurement systems, especially in High-Energy and Plasma Physics. Such FPGA-based systems require an extended control and diagnostics part corresponding to the complexity of the controlled system. Managing the complex [...] Read more.

FPGA-based data acquisition and processing systems play an important role in modern high-speed, multichannel measurement systems, especially in High-Energy and Plasma Physics. Such FPGA-based systems require an extended control and diagnostics part corresponding to the complexity of the controlled system. Managing the complex structure of registers while keeping the tight coupling between hardware and software is a tedious and potentially error-prone process. Various existing solutions aimed at helping that task do not perfectly match all specific requirements of that application area. The paper presents a new solution based on the XML system description, facilitating the automated generation of the control system’s HDL code and software components and enabling easy integration with the control software. The emphasis is put on reusability, ease of maintenance in the case of system modification, easy detection of mistakes, and the possibility of use in modern FPGAs. The presented system has been successfully used in data acquisition and preprocessing projects in high-energy physics experiments. It enables easy creation and modification of the control system definition and convenient access to the control and diagnostic blocks. The presented system is an open-source solution and may be adopted by the user for particular needs. Full article

(This article belongs to the Special Issue Advances in Electronics, Signal Processing and Control Applied in Sensors and Systems)

► Show Figures

Figure 1

18 pages, 1646 KiB

Open AccessArticle

Correlating Time Series Signals and Event Logs in Embedded Systems

by Kazimierz Krosman and Janusz Sosnowski

Sensors 2021, 21(21), 7128; https://doi.org/10.3390/s21217128 - 27 Oct 2021

Viewed by 3438

Abstract

In many embedded systems, we face the problem of correlating signals characterising device operation (e.g., performance parameters, anomalies) with events describing internal device activities. This leads to the investigation of two types of data: time series, representing signal periodic samples in a background [...] Read more.

In many embedded systems, we face the problem of correlating signals characterising device operation (e.g., performance parameters, anomalies) with events describing internal device activities. This leads to the investigation of two types of data: time series, representing signal periodic samples in a background of noise, and sporadic event logs. The correlation process must take into account clock inconsistencies between the data acquisition and monitored devices, which provide time series signals and event logs, respectively. The idea of the presented solution is to classify event logs based on the introduced similarity metric and deriving their distribution in time. The identified event log sequences are matched with time intervals corresponding to specified sample patterns (objects) in the registered signal time series. The matching (correlation) process involves iterative time offset adjustment. The paper presents original algorithms to investigate correlation problems using the object-oriented data models corresponding to two monitoring sources. The effectiveness of this approach has been verified in power consumption analysis using real data collected from the developed Holter device. It is quite universal and can be easily adapted to other device optimisation problems. Full article

(This article belongs to the Special Issue Advances in Electronics, Signal Processing and Control Applied in Sensors and Systems)

► Show Figures

Figure 1

19 pages, 3219 KiB

Open AccessArticle

A Secure Communication System for Constrained IoT Devices—Experiences and Recommendations

by Michał Goworko and Jacek Wytrębowicz

Sensors 2021, 21(20), 6906; https://doi.org/10.3390/s21206906 - 18 Oct 2021

Cited by 10 | Viewed by 4391

Abstract

The Internet of Things networks connect a large number of devices and can be used for various purposes. IoT systems collect and process vast amounts of often sensitive data. Information security should be the key feature of an IoT network. In this paper, [...] Read more.

The Internet of Things networks connect a large number of devices and can be used for various purposes. IoT systems collect and process vast amounts of often sensitive data. Information security should be the key feature of an IoT network. In this paper, we present the IoT-Crypto—secure communication system for the Internet of Things. It addresses IoT features, such as constrained abilities of devices, needs to reduce the volume of the transmitted data and be compatible with the Internet. IoT-Crypto introduces an innovative, lightweight certificate format and trust model based on real-world business relations. It also specifies secure communication protocol, which uses underlying encrypted DTLS connection. This paper presents IoT-Crypto in the context of comparable solutions, discusses its distinctive features and implementation details. Results of tests and experiments performed in the IoT-Crypto network confirm that it works correctly and securely. Test network was also used to ascertain the suitability of encoding standards and BLE IPSP profile for the IoT. Directions of future work were discussed based on those results. Full article

(This article belongs to the Special Issue Advances in Electronics, Signal Processing and Control Applied in Sensors and Systems)

► Show Figures

Figure 1

32 pages, 1184 KiB

Open AccessArticle

Messaging Protocols for IoT Systems—A Pragmatic Comparison

by Jacek Wytrębowicz, Krzysztof Cabaj and Jerzy Krawiec

Sensors 2021, 21(20), 6904; https://doi.org/10.3390/s21206904 - 18 Oct 2021

Cited by 25 | Viewed by 7006

Abstract

There are a dozen messaging protocols proposed for IoT systems. Choosing one for a new design is complicated, and a non-optimal selection can result in slower development and higher design costs. This paper aims to help select appropriate protocols, considering IoT applications’ specificity [...] Read more.

There are a dozen messaging protocols proposed for IoT systems. Choosing one for a new design is complicated, and a non-optimal selection can result in slower development and higher design costs. This paper aims to help select appropriate protocols, considering IoT applications’ specificity and communication requirements. We have identified the protocol features that are significant for the design and operation of IoT systems. This paper gives a substantial comparison of the protocols using the features and is based on a thorough analysis of the protocol specifications. The results contain an assessment of the suitability of the protocols for the defined types of IoT devices and the identified communication purposes. We conclude the comparison with some recommendations of the protocol selection and usage. Full article

(This article belongs to the Special Issue Advances in Electronics, Signal Processing and Control Applied in Sensors and Systems)

► Show Figures

Figure 1

23 pages, 652 KiB

Open AccessArticle

Computationally Efficient Nonlinear Model Predictive Control Using the L₁ Cost-Function

by Maciej Ławryńczuk and Robert Nebeluk

Sensors 2021, 21(17), 5835; https://doi.org/10.3390/s21175835 - 30 Aug 2021

Cited by 14 | Viewed by 3819

Abstract

Model Predictive Control (MPC) algorithms typically use the classical L

_{2}

cost function, which minimises squared differences of predicted control errors. Such an approach has good numerical properties, but the L

_{1}

norm that measures absolute values of the control errors gives better [...] Read more.

Model Predictive Control (MPC) algorithms typically use the classical L

_{2}

cost function, which minimises squared differences of predicted control errors. Such an approach has good numerical properties, but the L

_{1}

norm that measures absolute values of the control errors gives better control quality. If a nonlinear model is used for prediction, the L

_{1}

norm leads to a difficult, nonlinear, possibly non-differentiable cost function. A computationally efficient alternative is discussed in this work. The solution used consists of two concepts: (a) a neural approximator is used in place of the non-differentiable absolute value function; (b) an advanced trajectory linearisation is performed on-line. As a result, an easy-to-solve quadratic optimisation task is obtained in place of the nonlinear one. Advantages of the presented solution are discussed for a simulated neutralisation benchmark. It is shown that the obtained trajectories are very similar, practically the same, as those possible in the reference scheme with nonlinear optimisation. Furthermore, the L

_{1}

norm even gives better performance than the classical L

_{2}

one in terms of the classical control performance indicator that measures squared control errors. Full article

(This article belongs to the Special Issue Advances in Electronics, Signal Processing and Control Applied in Sensors and Systems)

► Show Figures

Figure 1

27 pages, 3494 KiB

Open AccessArticle

LSTM and GRU Neural Networks as Models of Dynamical Processes Used in Predictive Control: A Comparison of Models Developed for Two Chemical Reactors

by Krzysztof Zarzycki and Maciej Ławryńczuk

Sensors 2021, 21(16), 5625; https://doi.org/10.3390/s21165625 - 20 Aug 2021

Cited by 70 | Viewed by 13395

Abstract

This work thoroughly compares the efficiency of Long Short-Term Memory Networks (LSTMs) and Gated Recurrent Unit (GRU) neural networks as models of the dynamical processes used in Model Predictive Control (MPC). Two simulated industrial processes were considered: a polymerisation reactor and a neutralisation [...] Read more.

This work thoroughly compares the efficiency of Long Short-Term Memory Networks (LSTMs) and Gated Recurrent Unit (GRU) neural networks as models of the dynamical processes used in Model Predictive Control (MPC). Two simulated industrial processes were considered: a polymerisation reactor and a neutralisation (pH) process. First, MPC prediction equations for both types of models were derived. Next, the efficiency of the LSTM and GRU models was compared for a number of model configurations. The influence of the order of dynamics and the number of neurons on the model accuracy was analysed. Finally, the efficiency of the considered models when used in MPC was assessed. The influence of the model structure on different control quality indicators and the calculation time was discussed. It was found that the GRU network, although it had a lower number of parameters than the LSTM one, may be successfully used in MPC without any significant deterioration of control quality. Full article

(This article belongs to the Special Issue Advances in Electronics, Signal Processing and Control Applied in Sensors and Systems)

► Show Figures

Figure 1

12 pages, 45633 KiB

Open AccessCommunication

Using Off-the-Shelf Graphic Design Software for Validating the Operation of an Image Processing System

by Jerzy Chrząszcz

Sensors 2021, 21(15), 5104; https://doi.org/10.3390/s21155104 - 28 Jul 2021

Cited by 1 | Viewed by 2340

Abstract

Fluorescent markers are widely used to protect banknotes, passports, and other documents. Verification of such documents relies upon visual assessment of the markers revealed by ultraviolet (UV) radiation. However, such an explicit approach is inappropriate in certain circumstances, e.g., when discretely checking people [...] Read more.

Fluorescent markers are widely used to protect banknotes, passports, and other documents. Verification of such documents relies upon visual assessment of the markers revealed by ultraviolet (UV) radiation. However, such an explicit approach is inappropriate in certain circumstances, e.g., when discretely checking people for marks left by a pepper gel thrower. The UV light and fluorescent light must not be visible in such applications, yet reliable detection of the markers must still be performed. This problem was successfully resolved using TRIZ methodology, which led to a patent application. The main idea of the solution is to use low-intensity time-variable UV light for illuminating an object and process the image of the object acquired by a camera to detect colour changes too small to be noticed with the naked eye. This paper describes how popular graphics editors such as Adobe Photoshop Elements were used to validate the system concept devised. Simulation experiments used images taken in both visible and UV light to assess the effectiveness and perceptibility of the detection process. The advantage of such validation comes from using commodity software and performing the experiments without access to a laboratory and without physical samples, which makes this approach especially suitable in pandemic times. Full article

(This article belongs to the Special Issue Advances in Electronics, Signal Processing and Control Applied in Sensors and Systems)

► Show Figures

Figure 1

24 pages, 6359 KiB

Open AccessArticle

Static and Dynamic Verification of Space Systems Using Asynchronous Observer Agents

by Wiktor B. Daszczuk

Sensors 2021, 21(13), 4541; https://doi.org/10.3390/s21134541 - 2 Jul 2021

Cited by 3 | Viewed by 2581

Abstract

Formal verification of distributed systems is essential, especially in mission-critical systems that cannot be restarted. Such are space systems in which satellites read sensor values and autonomously make actuator decisions based on them, and ground services only set general patterns of behavior. The [...] Read more.

Formal verification of distributed systems is essential, especially in mission-critical systems that cannot be restarted. Such are space systems in which satellites read sensor values and autonomously make actuator decisions based on them, and ground services only set general patterns of behavior. The verification formalism should correspond to the essential characteristics of a distributed system, such as node autonomy and asynchrony of actions and communication, as in our Integrated Model of Distributed Systems (IMDS). It is also crucial that the formalism allows for finding partial deadlocks and checking partial termination, where only a subset of the system nodes is involved while the rest can perform their own tasks at the same time. This article presents the idea of using monitoring agents—observers prepared in the IMDS formalism. Observers check the state of individual system components by polling, allowing verification without knowing the global state of the system. Such an agent is an ideal prototype of a runtime observer that checks if the actual operation of the system corresponds to a design that has previously been proven correct. Full article

(This article belongs to the Special Issue Advances in Electronics, Signal Processing and Control Applied in Sensors and Systems)

► Show Figures

Figure 1

14 pages, 5115 KiB

Open AccessArticle

Photonic Integrated Interrogator for Monitoring the Patient Condition during MRI Diagnosis

by Mateusz Słowikowski, Andrzej Kaźmierczak, Stanisław Stopiński, Mateusz Bieniek, Sławomir Szostak, Krzysztof Matuk, Luc Augustin and Ryszard Piramidowicz

Sensors 2021, 21(12), 4238; https://doi.org/10.3390/s21124238 - 21 Jun 2021

Cited by 13 | Viewed by 3884

Abstract

In this work, we discuss the idea and practical implementation of an integrated photonic circuit-based interrogator of fiber Bragg grating (FBG) sensors dedicated to monitoring the condition of the patients exposed to Magnetic Resonance Imaging (MRI) diagnosis. The presented solution is based on [...] Read more.

In this work, we discuss the idea and practical implementation of an integrated photonic circuit-based interrogator of fiber Bragg grating (FBG) sensors dedicated to monitoring the condition of the patients exposed to Magnetic Resonance Imaging (MRI) diagnosis. The presented solution is based on an Arrayed Waveguide Grating (AWG) demultiplexer fabricated in generic indium phosphide technology. We demonstrate the consecutive steps of development of the device from design to demonstrator version of the system with confirmed functionality of monitoring the respiratory rate of the patient. The results, compared to those obtained using commercially available bulk interrogator, confirmed both the general concept and proper operation of the device. Full article

(This article belongs to the Special Issue Advances in Electronics, Signal Processing and Control Applied in Sensors and Systems)

► Show Figures

Figure 1

20 pages, 8662 KiB

Open AccessArticle

Fast Real-Time Model Predictive Control for a Ball-on-Plate Process

by Krzysztof Zarzycki and Maciej Ławryńczuk

Sensors 2021, 21(12), 3959; https://doi.org/10.3390/s21123959 - 8 Jun 2021

Cited by 13 | Viewed by 5632

Abstract

This work is concerned with an original ball-on-plate laboratory process. First, a simplified process model based on state–space process description is derived. Next, a fast state–space MPC algorithm is discussed. Its main advantage is computational simplicity: the manipulated variables are found on-line using [...] Read more.

This work is concerned with an original ball-on-plate laboratory process. First, a simplified process model based on state–space process description is derived. Next, a fast state–space MPC algorithm is discussed. Its main advantage is computational simplicity: the manipulated variables are found on-line using explicit formulas with parameters calculated off-line; no real-time optimization is necessary. Software and hardware implementation details of the considered MPC algorithm using the STM32 microcontroller are presented. Tuning of the fast MPC algorithm is discussed. To show the efficacy of the MPC algorithm, it is compared with the classical PID and LQR controllers. Full article

(This article belongs to the Special Issue Advances in Electronics, Signal Processing and Control Applied in Sensors and Systems)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advances in Electronics, Signal Processing and Control Applied in Sensors and Systems

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (15 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI