The manufacturing industry is competitive and is constantly striving to improve OEE. In the transition to smart production, digital technologies such as IIoT are highlighted as important. IIoT platforms enable real-time monitoring. In this sense, digital technologies such as IIoT are expected to improve OEE by enabling the analysis of real-time data and production availability.  A qualitative study with an abductive approach has been conducted. The empirical material has been collected through a case study of a heavy-duty vehicle industry and the theoretical framework is based on a literature study. Lastly, a thematic analysis has been used for the derivation of appropriate themes for analysis. The study concluded that challenges and enablers related to the implementation of IIoT to improve OEE can be divided into technical and cultural factors. Technical challenges and enablers mainly consider the achievement of interoperability, compatibility, and cyber security, while cultural factors revolve around digital acceptance, competence, encouragement of digital curiosity, and creating knowledge and understanding towards OEE. Lastly, conclusions can be drawn that implementation of IIoT has a positive effect on OEE since it ensures consistent and accurate data, which lies a solid foundation for production decisions. Also, digitalization of production enhances lean practices which are considered a key element for improving OEE.

Lite-Agro studies applications of TinyML in pear (Pyrus communis) tree disease identification and explores hardware implementations with an ESP32 microcontroller. The study works with the DiaMOS Pear Dataset to learn through image analysis whether the leaf is healthy or not, and classifies it according to curl, healthy, spot or slug categories. The system is designed as a low cost and light-duty computing detection edge solution that compares models such as InceptionV3, XceptionV3, EfficientNetB0, and MobileNetV2. This work also researches integration with federated learning frameworks and provides an introduction to federated averaging algorithms.

<p dir="ltr">In recent years, a surge in data-driven computation has significantly impacted security analysis in cyber-physical systems (CPSs), especially in decentralized environments. This transformation can be attributed to the remarkable computational power offered by high-performance computers (HPCs), coupled with advancements in distributed computing techniques and sophisticated learning algorithms like deep learning and reinforcement learning. Within this context, wireless communication systems and decentralized computing systems emerge as highly suitable environments for leveraging data-driven computation in security analysis. Our research endeavors have focused on exploring the vast potential of various deep learning algorithms within the CPS domains. We have not only delved into the intricacies of existing algorithms but also designed novel approaches tailored to the specific requirements of CPSs. A pivotal aspect of our work was the development of a comprehensive decentralized computing platform prototype, which served as the foundation for simulating complex networking scenarios typical of CPS environments. Within this framework, we harnessed deep learning techniques such as restricted Boltzmann machine (RBM) and deep convolutional neural network (DCNN) to address critical security concerns such as the detection of Quality of Service (QoS) degradation and Denial of Service (DoS) attacks in smart grids. Our experimental results showcased the superior performance of deep learning-based approaches compared to traditional pattern-based methods. Additionally, we devised a decentralized computing system that encompassed a novel decentralized learning algorithm, blockchain-based learning automation, distributed storage for data and models, and cryptography mechanisms to bolster the security and privacy of both data and models. Notably, our prototype demonstrated excellent efficacy, achieving a fine balance between model inference performance and confidentiality. Furthermore, we delved into the integration of domain knowledge from CPSs into our deep learning models. This integration shed light on the vulnerability of these models to dedicated adversarial attacks. Through these multifaceted endeavors, we aim to fortify the security posture of CPSs while unlocking the full potential of data-driven computation in safeguarding critical infrastructures.</p>

In this research, three aspects of data quality with regard to artifical intelligence (AI) have been investigated: detection of misleading fake data, especially deepfakes, data scarcity, and data insufficiency, especially how much training data is required for an AI application. Different application domains where the selected aspects pose issues have been chosen. To address the issues of data privacy, security, and regulation, these solutions are targeted for edge devices. In Chapter 3, two solutions have been proposed that aim to preempt such misleading deepfake videos and images on social media. These solutions are deployable at edge devices. In Chapter 4, a deepfake resilient digital ID system has been described. Another data quality aspect, data scarcity, has been addressed in Chapter 5. One of such agricultural problems is estimating crop damage due to natural disasters. Data insufficiency is another aspect of data quality. The amount of data required to achieve acceptable accuracy in a machine learning (ML) model has been studied in Chapter 6. As the data scarcity problem is studied in the agriculture domain, a similar scenario—plant disease detection and damage estimation—has been chosen for this verification. This research aims to provide ML or deep learning (DL)-based methods to solve several data quality-related issues in different application domains and achieve high accuracy. We hope that this work will contribute to research on the application of machine learning techniques in domains where data quality is a barrier to success.

No description available.

Cyber-Physical System (CPS) or Digital-Twin approach are becoming popular in industry 4.0 revolution. CPS not only allow to view the online status of equipment, but also allow to predict the health of tool. Based on the real time sensor data, it aims to detect anomalies in the industrial operation and prefigure future failure, which lead it towards smart maintenance. CPS can contribute to sustainable environment as well as sustainable production, due to its real-time analysis on production. In this thesis, we analyzed the behavior of a tool of Ringvalsverk 4, at Ovako with its twin model (known as Digital-Twin) over a series of data. Initially, the data contained unwanted signals which is then cleaned in the data processing phase, and only before production signal is used to identify the tool’s model. Matlab’s system identification toolbox is used for identifying the system model, the identified model is also validated and analyzed in term of stability, which is then used in CPS. The Digital-Twin model is then used and its output being analyzed together with tool’s output to detect when its start deviate from normal behavior.

Den globala industrin har under det senaste decenniet genomgått en enorm digital transformation, där tillämpandet av digitala och smarta verktyg inom företag aldrig har varit mer påtagligt. Under november 2011 presenterades begreppet Industrial 4.0 i en artikel skriven av den Tyska regeringen som beskriver en teknikintensiv strategi för år 2020 och omfattar vad idag betraktas som den fjärde industriella revolutionen. Industri 4.0 utgörs till stor del av integrationsprocessen mellan teknik och övrig verksamhet inom ett tillverkningsföretag, vilket i sin tur ger upphov till teknik såsom; automation, förstärkt verklighet, simuleringar, intelligenta tillverkningsprocesser samt övriga processindustriella IT-verktyg och -system. Flertal forskningsstudier hävdar att Industri 4.0-teknologier har potential att revolutionera sättet företag idag tillverkar produkter, men i och med att begreppet är relativt nytt, abstrakt samt består av väldigt komplexa tekniker och komponenter, är införandet av dessa inom en tillverkningsmiljö för närvarande en stor utmaning för tillverkande företag. Denna studie syftar alltså till att belysa de utmaningar och hinder som större tillverkande företag möter vid implementering av digital och smart teknik, samt åtgärder för att motverka dessa. Målet med studien är att leverera ett användbart resultat både för aktiva företag inom tillverkningsindustrin i form av stöd vid analys och diskussion av eventuella implementeringsstrategier och -satsningar inom Industri 4.0, men också ge övriga intressenter en uppfattning kring ämnet med tanke på att det, som sagt, är ett abstrakt system. En litteraturstudie genomfördes både för att få en överblick kring ämnet Industri 4.0 och hur det har behandlats i tidigare examensarbeten, avhandlingar samt forskningsstudier, men även för att identifiera tidigare identifierade hinder. Därefter genomfördes fältstudier på två tillverkande företag, Scania och Atlas Copco, samt teknikkonsultföretaget Knightec. Syftet med detta var framförallt att få en mer påtaglig och verklighetsförankrad uppfattning av Industri 4.0 men även verifiera att informationen i den teoretiska delen är relevant i praktiken för en tillverkande verksamhet. Studien påvisade därtill att identifierade utmaningar och hinder återfinns bland flertal organisatoriska områden inom ett tillverkande företag, varav de mest framgående aspekterna omfattade strategi, ledarskap, kunder, kultur, anställda, juridik samt teknik. Resultatet avslöjade vidare att tillverkande företag präglas av bristfälliga planer och strategier för att identifiera samt implementera nya tekniska lösningar, konflikter bland de anställda, svårigheter att integrera kundsystem enhetligt inom produktionen, avsaknad av lämplig teknisk kompetens, juridiska problem vad gäller hantering av data samt svårigheter att integrera nya och gamla teknologier. / The global industry has during the last decade undergone a considerable digital transformation, whereas the application of digital and smart technology within companies has never been more of a relevant field. During November of 2011, the term Industrial 4.0 was presented in an article written by the German government to describe a technology intensive strategy for the year 2020 and signifies what today is defined as the fourth industrial revolution. Industry 4.0 largely consists of the integration process between technology and remaining operations within a manufacturing company, which enables the development of technologies such as; automation, augmented reality, simulations, intelligent manufacturing processes and other process industrial IT-tools and systems. Several research studies has suggested that Industry 4.0 technologies has the potential to revolutionize the way companies today manufacture products, however, since the concept is relatively new, abstract and consists of various complex technologies and components, the implementation process of these within a manufacturing environment is one largest challenges that manufacturing companies are facing. This study therefore aims to highlight the challenges and difficulties that large manufacturing companies are facing when implementing digital and smart technology, as well as provide solutions regarding how they can be overcome. The overall goal is to deliver useful results both for active companies within the manufacturing industry in regards to serving as support when analyzing and discussing possible implementation strategies as well investments related to Industry 4.0, but also to provide surrounding stakeholders with a perception of the subject. At the commencement of the project, a literature study was performed to develop an overview of how Industry 4.0 has been discussed in previous theses and research studies as well as to find previously identified difficulties regarding the implementation process. Finally, a field study was performed at Scania and Atlas Copco and at the technology consulting firm Knightec. The main purpose was to gain a more realistic perspective regarding how digitalization and Industry 4.0 systems are applied and to verify that the information from our theoretical study is relevant and applicable within an actual manufacturing company. The study furthermore revealed that the identified difficulties and challenges can be found within multiple organizational areas of a manufacturing company, whereas the most distinct aspects consisted of strategy, leadership, customers, culture, employees, legal governance as well as technology. The results showed that companies were characterized by an overall lack of strategy to implement new technologies, conflicts with employees during implementation, difficulties to integrate customer orders with production, lack of technical skills in staff, legal issues regarding data storage and difficulties integrating new and old technologies.

Den fjärde industriella revolutionen, även kallad Industri 4.0, drivs av ett antal teknologier som medför digitalisering och automatisering av industriella processer. Konceptet innebär en applicering av dataanalys med avancerade analytiska verktyg på stora mängder data, vilka påstås ge stora möjligheter för kvalitetsförbättringar. För att en sådan övergång ska ske är förmågan att hantera data avgörande. Trots det uppvisar många företag idag bristande användning av data för att ta beslut. Frågan är hur företag kan göra för att hantera data och utföra en transformation till Industri 4.0. För att studera det här ämnet har det här examensarbetet utförts som en fallstudie på en stansprocess hos Scania Ferruform. Genom en litteraturstudie, kvantitativ datainsamling samt observationer och intervjuer undersökte examensarbetet den nuvarande användning av data i processen. Därefter undersöktes data med statistiska verktyg för att visa på hur data kan hanteras i en process för att erhålla större kunskap om orsaker till avvikelser. Examensarbetet utredde till sist hur fortsatt arbete med datahantering kan utföras för att uppnå målet Industri 4.0.Analysverktyg har använts för att analysera över 39 000 datapunkter. Resultatet visar på att det finns utvecklingsmöjligheter vad gäller insamling, kvalitet och användning av data. Ett ramverk presenteras för hur företaget bör hantera data för att kunna utvinna ny kunskap från deras processer samt hur Ferruform fortsatt kan arbeta mot Industri 4.0.Slutligen ges rekommendationer om fortsatta studier. Resultatet av examensarbetet blir ett stöd för Ferruform i deras arbete mot mer dugliga processer och den tekniska utveckling företaget eftersträvar. / The fourth industrial revolution, also called Industry 4.0 is powered by several technologies which result in digitalization and automatization of industrial processes. The concept includes the application of big data and advanced analytics, which are said to provide great opportunities for quality improvements. For such a transition to take place, the ability to handle data is crucial. Despite this, many companies today show a lack of use of data to drive decision-making. The question is how companies can manage data and ultimately transition towards Industry 4.0. To research this topic this thesis has been carried out as a case study of a punching process at Scania Ferruform. Through a literature review, quantitative data collection, as well as observations and interviews, the thesis examined the current use of data in the process. Subsequently, data were examined with statistical tools to illustrate how data can be managed in a process to attain increased knowledge about causes of deviations. Lastly, the thesis explored future work towards Industry 4.0. Analysis tools have been used to analyse over 39 000 data points. The result of the study shows that there are opportunities for development in terms of collection, quality and use of data. A framework of how Ferruform should manage data in order to extract new knowledge from its processes is presented. Furthermore, an action plan is presented for a transition towards Industry 4.0. Finally, recommendations are given for further studies. The result of the thesis will be helpful for Ferruform in its transition towards more efficient processes and the technical development of which the company strives towards.

Объект исследования – кибер-физические системы, подверженные различным инцидентам, отказам и сбоям в своей работе. Цель работы – разработка модели машинного обучения для определения корневых причин сбоев в производственной системе, а также исследование возможности использования машинного обучения для определения причин будущих сбоев. Методы исследования: сбор, анализ и синтез данных, сравнение, обобщение, классификация, аналогия, эксперимент, измерение, описание. Результаты работы: разработана и обучена модель машинного обучения для анализа корневых причин инцидентов производственной установки методом классификации на выбранном наборе «сырых» данных небольшого объема с последующей проверкой качества ее работы на тестовых данных. Область применения – обучение модели корневым причинам инцидентов (отказов, сбоев) производственных систем на имеющихся данных с последующим оперативным обнаружением причин аномальной работы систем в тандеме с работой алгоритма по автоматическому обнаружению и прогнозированию аномалий. / The object of research is cyber-physical systems that are susceptible to various incidents, failures and malfunctions in their operation. The goal of the work is to develop a machine learning model to determine the root causes of failures in a production system, as well as to explore the possibility of using machine learning to determine the causes of future failures. Research methods: collection, analysis and synthesis of data, comparison, generalization, classification, analogy, experiment, measurement, description. Results of the work: a machine learning model was developed and trained to analyze the root causes of incidents in a production facility using the classification method on a selected set of small-volume “raw” data, followed by checking the quality of its work on test data. Scope of application: training a model for the root causes of incidents (failures, failures) of production systems using available data, followed by prompt detection of the causes of abnormal operation of systems in tandem with the work of the algorithm for automatic detection and prediction of anomalies.