Este trabalho propõe investigar, desenvolver e validar uma metodologia de projeto para sistemas de diagnóstico para detecção de falhas e anomalias em aplicações de acionamento de motores elétricos, comumente utilizados na indústria de manufatura. A metodologia proposta é baseada na coleta e interpretação de dados de processo de redes PROFINET, perfil PROFIdrive, e ferramentas de aprendizagem de máquinas. Técnicas de extração e redução de atributos são aplicadas nos dados de processo coletados. Estes atributos são utilizados em algoritmos para reconhecimento de padrões, os algoritmos investigados são o k-Nearest Neighbor, Redes Neurais Artificiais, Support Vector Machines, e adicionalmente uma adaptação da metodologia é feita utilizando um algoritmo para detecção de novidades. A avaliação da metodologia considerou quatro cenários para estudos de caso, para falhas comuns em aplicações de máquinas rotativas. Os resultados alcançados demonstram a eficácia da metodologia, que foi capaz de detectar as falhas e anomalias investigadas de maneira satisfatória, similares a trabalhos correlatos, com o diferencial de não exigirem sensores adicionais dedicados na coleta de dados. Desta maneira, o trabalho contribui para área de redes de comunicação industrial, mais especificamente o protocolo PROFINET, diagnósticos de anomalias em máquinas acionadas por motores elétricos, e ferramentas de aprendizagem de máquinas. / This work proposes to investigate, develop and validate a methodology to design diagnostic systems to detect faults and anomalies in motion control applications, commonly used in manufacturing industry. The proposed methodology is based on collection and interpretation of process data from PROFINET networks, PROFIdrive profile, and machine learning tools. Feature extraction and selection techniques are applied to the collected process data. These features are used in algorithms for pattern recognition problems. Investigated algorithms are k-Nearest Neighbor, Artificial Neural Networks, Support Vector Machines and in addition, an adaptation of the methodology is held for novelty detection. Four scenarios were considered as case of studies for methodology evaluation, based on common faults in rotating machine applications. The results proved the methodology effectiveness for diagnostic system design, which were able to detect satisfactorily the investigated faults and anomalies, similar to related work, with the differential of not requiring additional dedicated sensors for data collection. In this way, the work contributes to the area of industrial communication networks, more specifically in PROFINET protocol, diagnostic systems for fault detection in motion control applications, and machine learning tools.

In this thesis, we present a MAC-layer packet scheduling algorithm, called Best-effort Packet Scheduling Algorithm(BPA), for real-time switched Ethernet networks. BPA considers a message model where application messages have trans-node timeliness requirements that are specified using Jensen's benefit functions. The algorithm seeks to maximize aggregate message benefit by allowing message packets to inherit benefit functions of their parent messages and scheduling packets to maximize aggregate packet-level benefit. Since the packet scheduling problem is NP-hard, BPA heuristically computes schedules with a worst-case cost of O(n^2), faster than the O(n^3) cost of the best known Chen and Muhlethaler's Algorithm(CMA) for the same problem. Our simulation studies show that BPA performs the same or significantly better than CMA. We also construct a real-time switched Ethernet by prototyping an Ethernet switch using a Personal Computer(PC) and implementing BPA in the network protocol stack of the Linux kernel for packet scheduling. Our actual performance measurements of BPA using the network implementation reveal the effectiveness of the algorithm. Finally, we derive timeliness feasibility conditions of real-time switched Ethernet systems that use the BPA algorithm. The feasibility conditions allow real-time distributed systems to be constructed using BPA, with guaranteed soft timeliness. / Master of Science

Fast paced improvement of Ethernet technology has also received attention in the industry field like it did in other fields and ways of usage have started to be studied. As it is understood that the standard Ethernet protocols cannot be used due to the unsatisfied real time requirements, industrial and academic researchers have started to develop solutions to overcome this deficiency. In this thesis, the real hardware adaptations of Real Time Ethernet and RTXX protocol algorithms are implemented and their behaviors on the hardware are observed. Each parameter that affects the system&rsquo / s real time behavior is individually examined and the solution proposals are discussed.

Background: The train communication network is vulnerable to intrusion assaultsbecause of the openness of the ethernet communication protocol. Therefore, an intru-sion detection system must be incorporated into the train communication network.There are many algorithms available in Machine Learning(ML) to develop the Intru-sion Detection System(IDS). Majorly, depending on the accuracy and execution timeof the algorithm, it is decided as the best. Performance metrics like F1 score, preci-sion, recall, and support are compared to see how well the algorithm fits the modelwhile training. The following thesis will detect the anomalies in the Train ControlManagement System(TCMS) and then the comparison of various algorithms will beheld in order to declare the accurate algorithm. Objectives: In this thesis work, we aim to research anomaly detection in a train’sreal-time ethernet using an IDS. The main objectives of this thesis include per-forming Principal Component Analysis(PCA) and feature selection using RandomForest(RF) for simplifying the complexity of the dataset by reducing dimensionalityand extracting significant features. Followed by, choosing the most consistent algo-rithm for anomaly detection from the selected algorithms by evaluating performanceparameters, especially accuracy and execution time after training the models usingML algorithms. Method: This thesis necessitates one research methodology which is experimen-tation, to answer our research questions. For RQ1, experimentation will help usgain better insights into the dataset to extract valuable and essential features as apart of feature selection using RF and dimensionality reduction using PCA. RQ2also uses experimentation because it provides better accuracy and reliability. Afterpre-processing, the data will be used to train the algorithms and will be evaluatedusing various methods. Results: In this study, we have analysed data using EDA, reduced dimensionalityand feature selection using PCA and RF algorithm respectively. We used five su-pervised machine learning methods namely, Support Vector Machine(SVM), NaiveBayes, Decision Tree, K-nearest Neighbor(KNN), and Random Forest(RF). Aftertesting and utilizing the "KDDCup 1999" pre-processed dataset from the Universityof California Irvine(UCI) ML repository, Decision Tree model has been concludedas the best-performing algorithm with an accuracy of 98.89% in 0.098 seconds, incomparison to other models. Conclusions: Five models have been trained using the five ML techniques foranomaly detection using an IDS. We concluded that the decision tree trained modelhas optimal performance with an accuracy of 98.89% and time of 0.098 seconds

Esta tese propõe uma metodologia de detecção de anomalias por meio da otimização da extração, seleção e classificação de características relacionadas ao tráfego de redes Real Time Ethernet (RTE). Em resumo, dois classificadores são treinados usando características que são extraídas do tráfego por meio da técnica de janela deslizante e posteriormente selecionadas de acordo com sua correlação com o evento a ser classificado. O número de características relevantes pode variar de acordo com os indicadores de desempenho de cada classificador. Reduzindo a dimensionalidade do evento a ser classificado com o menor número de características possíveis que o represente, são garantidos a redução do esforço computacional, ganho de tempo, dentre outros benefícios. Posteriormente, os classificadores são comparados em função dos indicadores de desempenho: acurácia, taxa de falsos positivos, taxa de falsos negativos, tempo de processamento e erro relativo. A metodologia proposta foi utilizada para identificar quatro diferentes eventos (três anomalias e o estado normal de operação) em redes PROFINET reais e com configurações distintas entre si; também foi aplicada em três eventos (duas anomalias e o estado normal de operação) em redes SERCOS III. O desempenho de cada classificador é analisado em suas particularidades e comparados com pesquisas correlatas. Por fim, é explorada a possibilidade de aplicação da metodologia proposta para outros protocolos baseados em RTE. / This thesis proposes an anomaly detection methodology by optimizing extraction, selection and classification of characteristics related to Real Time Ethernet (RTE) network traffic. In summary, two classifiers are trained using features which are extracted from network traffic through the sliding window technique and selected according to their correlation with the event being classified. The number of relevant characteristics could vary according to performance indicators of each classifier. Reducing the dimensionality of the event to be classified using the smallest number of characteristics which represent it, guarantees reduction in computational effort, processing time, among other benefits. The classifiers are compared according to performance indicators: accuracy, false positive rate, false negative rate, processing time and relative error. The proposed methodology was used to identify four different events (three anomalies and normal operation) in real PROFINET networks, using different configurations. It was also applied in 3 events (two anomalies and normal operation) in SERCOS III networks. The results obtained are analyzed in its particularities and compared with related research. Finally, the possibility of applying the proposed methodology for other protocols based on RTE is explored.

La conception d’un réseau de communication de sécurité basée sur l’Ethernet temps réel répondant aux exigences de la norme PESSRAL, dérivée de l’IEC 61508, constitue la base de notre travail. Afin d’atteindre cet objectif, nous mettons en oeuvre des mécanismes permettant de réduire la probabilité d’erreur et d’atteindre les niveaux d’intégrité de sécurité (SIL) par l’utilisation d’un système électronique déterministe. Avec un seul canal de communication, notre système doit être capable d’intégrer des fonctions critiques et non critiques sans remettre en cause la certification du système.Lors de cet engagement nous proposons un système de communication industrielle basé sur l’Ethernet temps réel. Les interfaces de communication proposées répondent aux exigences de réactivité, de déterminisme pour garantir les contraintes temporelles imposées par le processus et la norme. Pour assurer la sécurité fonctionnelle des interfaces, nous avons proposé une surcouche de type "safety" qui implémente des fonctions de sécurité selon le concept du canal noir défini dans l’IEC 61508. En nous basant sur ces propriétés, nous avons réussi à classifier les solutions temps réel à base d’Ethernet en trois classes en fonction du temps de cycle. La surcouche "safety", basée sur la redondance de données, a permis de renoncer à la solution de redondance physique. Cette redondance de données duplique le temps de cycle initial du réseau qui satisfait néanmoins aux conditions de sécurité et temporelles de la norme. / The design of a communication network with a real-time Ethernet-based security that meets the requirements of the PESSRAL standard, derived from IEC 61508, is the basis of our work. In order to achieve this goal, we implement mechanisms reducing the residual error probability and achieving Safety Integrity Levels (SIL) via a deterministic electronic system. Through a single communication channel, our system must be able to integrate critical and non-critical functions without compromising the system certification.According to this commitment, we suggest an industrial communication system based on real-time Ethernet. The proposed communication interfaces meet the requirements of responsiveness and determinism in order to guarantee the temporal constraints imposed by the process and the standard. To ensure the functional safety of the interfaces, we have proposed a "safety" overlay that implements security functions according to the concept of the black channel defined in IEC 61508. Based on these properties, we have managed to classify the Ethernet-based real-time solutions into three classes in terms of cycle time. The overlay "safety", based on the redundancy of data, made it possible to give up the solution of physical redundancy. This data redundancy duplicates the initial cycle time of the network, which nonetheless satisfies the security and time conditions of the standard.

The Dynamic Distributed Dependable Real-Time Industrial communication Protocol (D3RIP) provides service guarantees for Real-Time traffic and integrates the dynamically changing requirements of automation applications in their operation to efficiently utilize the resources. The protocol dynamically allocates the network resources according to the respective system state. To this end, the protocol architecture consists of an Interface Layer that provides time-slotted operation and a Coordination Layer that assigns each time slot to a unique transmitter device based on a distributed computation. In this thesis, a software simulator for D3RIP is developed. Using the D3RIP Simulator, modifications in D3RIP can be easily examined without facing complexities in real implementations and extensive effort in terms of time and cost. The simulator simulates the Interface Layer, the Coordination Layer and additionally, the Shared Medium. Hence, using the simulator, the system-protocol couple can be easily analyzed, tested and further improvements on D3RIP can be achieved with the least amount of effort. The simulator implements the Timed Input Output Automata (TIOA) models of the D3RIP stack components using C++. The resulting code is compiled on GCC (Gnu Compiler Collection). The logs of the simulation runs and the real system with 2 devices connected via cross 100MbE cables are compared. In a 3ms time slot, the simulator and the system incidents differ about 135&micro / s on the average, causing no asynchronousity in their instantaneous operational states. The D3RIP Simulator is useful in keeping track of any variable in the D3RIP system automaton at any instant up to 1&micro / s resolution.

Tato práce se zabývá analyzováním IEEE 802.1Q standardu TSN skupiny a návrhem testovacího modulu. Testovací modul je napsán v jazyku VHDL a je možné jej implementovat do Intel Stratix® V GX FPGA (5SGXEA7N2F45C2) vývojové desky. Standard IEEE 802.1Q (TSN) definuje deterministickou komunikace přes Ethernet sít, v reálném čase, požíváním globálního času a správným rozvrhem vysíláním a příjmem zpráv. Hlavní funkce tohoto standardu jsou: časová synchronizace, plánování provozu a konfigurace sítě. Každá z těchto funkcí je definovaná pomocí více různých podskupin tohoto standardu. Podle definice IEEE 802.1Q standardu je možno tyto podskupiny vzájemně libovolně kombinovat. Některé podskupiny standardu nemohou fungovat nezávisle, musí využívat funkce jiných podskupin standardu. Realizace funkce podskupin standardu je možná softwarově, hardwarově, nebo jejich kombinací. Na základě výše uvedených fakt, implementace podskupin standardu, které jsou softwarově související, byly vyloučené. Taky byly vyloučené podskupiny standardů, které jsou závislé na jiných podskupinách. IEEE 802.1Qbu byl vybrán jako vhodná část pro realizaci hardwarového testu. Různé způsoby testování byly vysvětleny jako DFT, BIST, ATPG a další jiné techniky. Pro hardwarové testování byla vybrána „Protocol Aware (PA)“technika, protože tato technika zrychluje testování, dovoluje opakovanou použitelnost a taky zkracuje dobu uvedení na trh. Testovací modul se skládá ze dvou objektů (generátor a monitor), které mají implementovanou IEEE 802.1Qbu podskupinu standardu. Funkce generátoru je vygenerovat náhodné nebo nenáhodné impulzy a potom je poslat do testovaného zařízeni ve správném definovaném protokolu. Funkce monitoru je přijat ethernet rámce a ověřit jejich správnost. Objekty jsou navrhnuty stejným způsobem na „TOP“úrovni a skládají se ze čtyř modulů: Avalon MM rozhraní, dvou šablon a jednoho portu. Avalon MM rozhraní bylo vytvořeno pro komunikaci softwaru s hardwarem. Tento modul přijme pakety ze softwaru a potom je dekóduje podle definovaného protokolu a „pod-protokolu “. „Pod-protokol“se skládá z příkazu a hodnoty daného příkazu. Podle dekódovaného příkazu a hodnot daných příkazem je kontrolovaný celý objekt. Šablona se používá na generování nebo ověřování náhodných nebo nenáhodných dat. Dvě šablony byly implementovány pro expresní ověřování nebo preempční transakce, definované IEEE 802.1Qbu. Porty byly vytvořené pro komunikaci mezi testovaným zařízením a šablonou podle daného standardu. Port „generátor“má za úkol vybrat a vyslat rámce podle priority a času vysílaní. Port „monitor“přijme rámce do „content-addressable memory”, která ověřuje priority rámce a podle toho je posílá do správné šablony. Výsledky prokázaly, že tato testovací technika dosahuje vysoké rychlosti a rychlé implementace.