Yes / Development of robust diagnostic solutions to monitor the health of systems and components to ensure through life cost effectiveness is often technically difficult, requiring an effective integration of design development with research and innovation. This paper presents a structured application of TRIZ and USIT (Unitied Structured Inventive Thinking) to generate concept solutions fur an in-service diagnostic system for a synchronous belt drive system for an automotive application. The systematic exploration through TRIZ and USIT methods has led to the development of six concept solution ideas directed at the functional requirement to determine the state or condition of the belt. The paper demonstrates that the combined deployment of TRIZ and USIT frameworks is a valuable approach addressing difficult design problems. (C) 2013 The Authors. Published by Elsevier B.V. Open access under CC BY-NC-ND license.

No description available.

No / Extensive research has been performed for developing knowledge based intelligent monitoring systems for improving the reliability of manufacturing processes. Due to the high expense of obtaining knowledge from human experts, it is expected to develop new techniques to obtain the knowledge automatically from the collected data using data mining techniques. Inductive learning has become one of the widely used data mining methods for generating decision rules from data. In order to deal with the noise or uncertainties existing in the data collected in industrial processes and systems, this paper presents a new method using fuzzy logic techniques to improve the performance of the classical inductive learning approach. The proposed approach, in contrast to classical inductive learning method using hard cut point to discretize the continuous-valued attributes, uses soft discretization to enable the systems have less sensitivity to the uncertainties and noise. The effectiveness of the proposed approach has been illustrated in an application of monitoring the machining conditions in uncertain environment. Experimental results show that this new fuzzy inductive learning method gives improved accuracy compared with using classical inductive learning techniques.

Thesis. (M. Tech. (Mechanical Engineering))--Vaal University of Technology / Bearing condition monitoring and fault diagnosis have been studied for many years. Popular techniques are applied through advanced signal processing and pattern recognition technologies. The subject of the research was vibration condition monitoring of incipient damage in rolling element bearings. The research was confined to deep-groove ball bearings because of their common applications in industry. The aim of the research was to apply neural networks to vibration condition monitoring of rolling element bearings. Kohonen's Self-Organising Feature Map is the neural network that was used to enable an automatic condition monitoring system. Bearing vibration is induced during bearing operation and the main cause is bearing friction, which ultimately causes wear and incipient spalling in a rolling element bearing. To obtain rolling element bearing vibrations a condition monitoring test rig for rolling element bearings had to be designed and built. A digital vibration measurement acquisition environment was created in Labview and Matlab. Data from the bearing test rig was recorded with a piezoelectric accelerometer, and an S-type load cell connected to dynamic signal analysis cards. The vibration measurement instrumentation was cost-effective and yielded accurate and repeatable measurements. Defects on rolling element bearings were artificially inflicted so that a pattern of bearing defects could be established. An input data format of vibration statistical parameters was created using the time and frequency domain signals. Kohonen's Self-Organising Feature Maps were trained in the input data, utilising an unsupervised, competitive learning algorithm and vector quantisation to cluster the bearing defects on a two-dimensional topographical map. A new practical dimension to condition monitoring of rolling element bearings was developed. The use of time domain and frequency domain analysis of bearing vibration has been combined with a visual and classification analysis of distinct bearing defects through the application of the Self-Organising Feature Map. This is a suitable technique for rolling element bearing defect detection, remaining bearing life estimation and to assist in planning maintenance schedules. / National Research Foundation; Council for Scientific and Industrial Research

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.

Milling is a widely used cutting process, most commonly applied to machining external surfaces of workpieces. When machining operations are required within hard to reach areas of components, or deep within the bore of components, alternative methods of metal removal are generally employed. Typically when milling at extended reaches, difficulties may increase exponentially when trying to achieve distances several meters into a component. Essentially every topic of the milling process becomes difficult and more convoluted. Firstly to generate a stable cutting condition, and ultimately for an operator to be able to understand the cutting conditions, when all normal senses to interpret the machining stability are removed. The aim for the research is, to enable the operation of high slenderness ratio internal milling operations to become a viable technology, by detailing the measures required, to obtain a stable cutting condition. The process needs to be monitored for degradation of the tooling due to wear, and to prevent catastrophic machine damage from tool breakage or machine component failure. This research addresses the lack of knowledge available for milling with extended reaches, and the knowledge gained to overcome the real difficulties that exist for this process. Initial experiments are conducted on a prototype machine to gain experience of the internal machining operation and the many issues that it faced. Establishing requirements of the process via investigation of the tooling and necessary auxiliary equipment, it becomes possible to consider countermeasures to address the errors generated by torsional twisting of the milling arm. A system for applying a counter torque to reduce torsional deflection errors has been employed to successfully reduce the unavoidable issue over such long distances. For the process to become manageable for an industrial operator without a high level of specialist knowledge, the application of tool condition monitoring (TCM) and process condition monitoring (PCM) had to be applied. This addresses a void in available literature and research with respect to internal machining, and enables the process to become practical for an industrial environment. For this reason the research project will concentrate on the application of TCM and PCM onto the machining system. The completion of the research resulted in the process becoming satisfyingly stable, and with a resulting accuracy that satisfies the requirements of the component. Performance of the final system rivalled or achieved better results than had been experienced by the project sponsor.

Der Betrieb von prozesstechnischen Produktionsanlagen wird stetig von verschiedenen Aufgaben begleitet, zum Beispiel der Steuerung und Optimierung der Produktion und der Aufrechterhaltung der Verfügbarkeit. Alle Gewerke, die sich mit dem Zustand der Anlage und des darin ablaufenden Prozesses beschäftigen, sind auf Daten angewiesen, die in der Anlage erfasst werden. Ein Großteil dieser Daten werden für die automatische Steuerungs-, Regelungs- und Sicherheitstechnik erfasst und darin in Echtzeit verarbeitet. Apparate und anderes Equipment sind zumeist nicht mit für deren Zustandsüberwachung dedizierter Messtechnik ausgestattet. Um Qualitätsmerkmale, Anlagenzustände oder Wartungsbedarfe erkennen zu können, müssen andere in der Anlage vorhandene Daten kombiniert und in Berechnungsmodellen kondensiert werden. Diese Methodik teilt sich in unterschiedliche Schritte auf: Datenakquise, Entwurf von Auswertemodellen, Modellintegration und Auswertung von Ergebnissen mit Ableitung von Aufgaben. Die vorliegende Arbeit ordnet sich in die Softwareaspekte dieser Methodik ein. Dabei versucht sie, die zentrale Frage „Wie könnte eine Infrastruktur auf Basis von verbreiteten Standardtechnologien aussehen, welche alle Schritte des Engineeringprozesses für freie Apparatemodelle automatisieren kann?“ anhand eines Vorschlags für eine Infrastruktur zu beantworten. Es wird eine Möglichkeit dargelegt, im Betrieb ohne Änderungen am bestehenden System kontinuierlich Daten für die Weiterverwendung in Apparatemodellen auszulesen. Der Entwurf und die Implementierung von Auswertemodellen wurde mit Hilfe eines entwickelten Werkzeugs unterstützt und dadurch die Struktur der Apparatemodelle vorgegeben, um eine einheitliche Modellintegration zu ermöglichen. Die Durchführung der Modellintegration erfolgte über die automatische Auswertung von Planungsdaten. Eine auf offenen Technologien basierende Ausführungsplattform für die Bewertungsmodelle wurde implementiert. Die Auswertung von Berechnungsergebnissen wurde über die Integration der Modelle in verbreitete, für Feldgeräte vorgesehene Standardwerkzeuge ermöglicht. Diese Infrastruktur ermöglicht es den verschiedenen Gewerken des Anlagenbetreibers, generische Bewertungsmodelle auf die Apparateinstanzen in der Anlage anzuwenden, und mit deren Berechnungsergebnissen ihre Aufgaben einfacher oder besser bearbeiten zu können. Nach einer Analyse der technischen Rahmenbedingungen wurde ein Konzept zur Modellintegration entwickelt und dessen Automatisierbarkeit diskutiert. Dieses Konzept wurde prototypisch umgesetzt. Es wurden Softwarekomponenten für den Betrieb sowie Softwarewerkzeuge für die Unterstützung sowohl der Erstellung als auch der Integration von Apparatemodellen entwickelt. Anhand dieser wurde Umsetzbarkeit des Konzepts überprüft / Operating process plants goes along with different tasks, e. g. control and optimization of the production and maintaining availability of the plant. There are several subsections of operations who deal with the state of the plant and the processes it runs. They are all dependent on information which is gathered throughout the plant. Most of this data is acquired for the automatic control, regulation, and safety gear and is processed in real-time. Apparatuses and other equipment are usually not equipped with measurement devices which are dedicated to monitor their state. For being able to recognize specific quality attributes, states of the plant, or maintenance needs, the existing measurements have to be combined and condensed by calculations. This methodology can be split into the following steps: data acquisition, design of evaluation models, integration of these models, and assessment of findings including inferring actions. This thesis addresses software aspects of this methodology. It tries to answer the key question „How to build an infrastructure, which shall be based on common standard technologies, in which all steps to engineer equipment models may be automated?“ by proposing a concrete infrastructure. A technique has been designed to continuously acquire data for further processing in equipment models without any changes to existing systems. The process of design and implementation of equipment models has been supported by a purpose-built tool. This tool puts out the designed models in a uniform structure to allow uniform model integration. This integration has been automated using the plant’s engineering data. An execution platform has been developed based on open technologies. Infrastructure and model structure have been designed to easily integrate calculation results into standard tools for being able to use them in common work environments. It enables the different subsections of operations in a plant to apply generic equipment assessment models on concrete equipment instances. Using the output of the models, they shall be enabled to perform their task in an easier or better manner. The technical requirements and prerequisites have been analyzed. Using the resulting conclusions, a concept to integrate models has been developed and the options to automate it have been discussed. This concept has been implemented prototypically. This implementation includes a runtime component and two tools to support development of models and their instantiation. It has been used to prove the feasibility of the concept.

Der Betrieb von prozesstechnischen Produktionsanlagen wird stetig von verschiedenen Aufgaben begleitet, zum Beispiel der Steuerung und Optimierung der Produktion und der Aufrechterhaltung der Verfügbarkeit. Alle Gewerke, die sich mit dem Zustand der Anlage und des darin ablaufenden Prozesses beschäftigen, sind auf Daten angewiesen, die in der Anlage erfasst werden. Ein Großteil dieser Daten werden für die automatische Steuerungs-, Regelungs- und Sicherheitstechnik erfasst und darin in Echtzeit verarbeitet. Apparate und anderes Equipment sind zumeist nicht mit für deren Zustandsüberwachung dedizierter Messtechnik ausgestattet. Um Qualitätsmerkmale, Anlagenzustände oder Wartungsbedarfe erkennen zu können, müssen andere in der Anlage vorhandene Daten kombiniert und in Berechnungsmodellen kondensiert werden. Diese Methodik teilt sich in unterschiedliche Schritte auf: Datenakquise, Entwurf von Auswertemodellen, Modellintegration und Auswertung von Ergebnissen mit Ableitung von Aufgaben. Die vorliegende Arbeit ordnet sich in die Softwareaspekte dieser Methodik ein. Dabei versucht sie, die zentrale Frage „Wie könnte eine Infrastruktur auf Basis von verbreiteten Standardtechnologien aussehen, welche alle Schritte des Engineeringprozesses für freie Apparatemodelle automatisieren kann?“ anhand eines Vorschlags für eine Infrastruktur zu beantworten. Es wird eine Möglichkeit dargelegt, im Betrieb ohne Änderungen am bestehenden System kontinuierlich Daten für die Weiterverwendung in Apparatemodellen auszulesen. Der Entwurf und die Implementierung von Auswertemodellen wurde mit Hilfe eines entwickelten Werkzeugs unterstützt und dadurch die Struktur der Apparatemodelle vorgegeben, um eine einheitliche Modellintegration zu ermöglichen. Die Durchführung der Modellintegration erfolgte über die automatische Auswertung von Planungsdaten. Eine auf offenen Technologien basierende Ausführungsplattform für die Bewertungsmodelle wurde implementiert. Die Auswertung von Berechnungsergebnissen wurde über die Integration der Modelle in verbreitete, für Feldgeräte vorgesehene Standardwerkzeuge ermöglicht. Diese Infrastruktur ermöglicht es den verschiedenen Gewerken des Anlagenbetreibers, generische Bewertungsmodelle auf die Apparateinstanzen in der Anlage anzuwenden, und mit deren Berechnungsergebnissen ihre Aufgaben einfacher oder besser bearbeiten zu können. Nach einer Analyse der technischen Rahmenbedingungen wurde ein Konzept zur Modellintegration entwickelt und dessen Automatisierbarkeit diskutiert. Dieses Konzept wurde prototypisch umgesetzt. Es wurden Softwarekomponenten für den Betrieb sowie Softwarewerkzeuge für die Unterstützung sowohl der Erstellung als auch der Integration von Apparatemodellen entwickelt. Anhand dieser wurde Umsetzbarkeit des Konzepts überprüft / Operating process plants goes along with different tasks, e. g. control and optimization of the production and maintaining availability of the plant. There are several subsections of operations who deal with the state of the plant and the processes it runs. They are all dependent on information which is gathered throughout the plant. Most of this data is acquired for the automatic control, regulation, and safety gear and is processed in real-time. Apparatuses and other equipment are usually not equipped with measurement devices which are dedicated to monitor their state. For being able to recognize specific quality attributes, states of the plant, or maintenance needs, the existing measurements have to be combined and condensed by calculations. This methodology can be split into the following steps: data acquisition, design of evaluation models, integration of these models, and assessment of findings including inferring actions. This thesis addresses software aspects of this methodology. It tries to answer the key question „How to build an infrastructure, which shall be based on common standard technologies, in which all steps to engineer equipment models may be automated?“ by proposing a concrete infrastructure. A technique has been designed to continuously acquire data for further processing in equipment models without any changes to existing systems. The process of design and implementation of equipment models has been supported by a purpose-built tool. This tool puts out the designed models in a uniform structure to allow uniform model integration. This integration has been automated using the plant’s engineering data. An execution platform has been developed based on open technologies. Infrastructure and model structure have been designed to easily integrate calculation results into standard tools for being able to use them in common work environments. It enables the different subsections of operations in a plant to apply generic equipment assessment models on concrete equipment instances. Using the output of the models, they shall be enabled to perform their task in an easier or better manner. The technical requirements and prerequisites have been analyzed. Using the resulting conclusions, a concept to integrate models has been developed and the options to automate it have been discussed. This concept has been implemented prototypically. This implementation includes a runtime component and two tools to support development of models and their instantiation. It has been used to prove the feasibility of the concept.

Condition monitoring (CM) of electrical equipment is an important field in electrical engineering and a considerable amount of research is dedicated to this field. Power cables are one of the most important parts of any electrical network and the variety of techniques available for CM of electrical cables is therefore no surprise. Electrical cables are exposed to operational and environmental stressors which will cause degradation of the insulation material. The degradation will continue to the point where the cable fails. Blackouts caused by failing cables will have an effect on the safety, efficiency and production of an electrical network. It is therefore important to constantly monitor the condition of electrical cables, in order to prevent the premature failure of cables. The research presented in this dissertation sets out to investigate CM techniques for power cables and to design and implement a basic cable CM technique based on the principles of partial discharge (PD) measurements. A comprehensive literature study introduces the fundamental concepts regarding the CM of power cables. The basic construction of electrical cables, as well as the variety of different types is researched in order to lay a foundation for the research that follow. CM techniques for electrical equipment are investigated, with the emphasis on techniques used on cables. Conducted research led to the decision to focus on CM by means of PD measurements. PD as a phenomenon is investigated to be able to better understand the origins and effects of discharge activity. From there the focus shifts to the available techniques for monitoring the condition of electrical cables by means of PD measurements. The research conducted in the literature study chapter forms the basis from which the rest of the study is conducted. Simulation models were used to study PD characteristics. The models are derived from engineering and mathematical principles and are based on the well-known three-capacitor model of PD. The simulations were performed in order to study the effects of discharge activity. The designed simulation models allows for a variety of PD characteristics to be studied. The simulations were performed in the MATLAB® Simulink® environment. The research conducted in the dissertation was used to design an elementary CM technique which can be used to detect the presence of PD within electrical cables. The designed CM technique was used for the practical measurement of PD data. MATLAB® programs were designed in order to analyse the PD data in both the time- and frequency-domain. The analysis of the measured data revealed PD characteristics of the test specimen used for the measurements. The designed CM is used for the detection of PD activity within electrical cables and in combination with other techniques, may be used for complete CM of electrical cables. The experimental setup which was used to take practical PD measurements adds another dimension to the work presented in this dissertation. / MIng (Electrical and Electronic Engineering), North-West University, Potchefstroom Campus, 2015

Condition monitoring (CM) of electrical equipment is an important field in electrical engineering and a considerable amount of research is dedicated to this field. Power cables are one of the most important parts of any electrical network and the variety of techniques available for CM of electrical cables is therefore no surprise. Electrical cables are exposed to operational and environmental stressors which will cause degradation of the insulation material. The degradation will continue to the point where the cable fails. Blackouts caused by failing cables will have an effect on the safety, efficiency and production of an electrical network. It is therefore important to constantly monitor the condition of electrical cables, in order to prevent the premature failure of cables. The research presented in this dissertation sets out to investigate CM techniques for power cables and to design and implement a basic cable CM technique based on the principles of partial discharge (PD) measurements. A comprehensive literature study introduces the fundamental concepts regarding the CM of power cables. The basic construction of electrical cables, as well as the variety of different types is researched in order to lay a foundation for the research that follow. CM techniques for electrical equipment are investigated, with the emphasis on techniques used on cables. Conducted research led to the decision to focus on CM by means of PD measurements. PD as a phenomenon is investigated to be able to better understand the origins and effects of discharge activity. From there the focus shifts to the available techniques for monitoring the condition of electrical cables by means of PD measurements. The research conducted in the literature study chapter forms the basis from which the rest of the study is conducted. Simulation models were used to study PD characteristics. The models are derived from engineering and mathematical principles and are based on the well-known three-capacitor model of PD. The simulations were performed in order to study the effects of discharge activity. The designed simulation models allows for a variety of PD characteristics to be studied. The simulations were performed in the MATLAB® Simulink® environment. The research conducted in the dissertation was used to design an elementary CM technique which can be used to detect the presence of PD within electrical cables. The designed CM technique was used for the practical measurement of PD data. MATLAB® programs were designed in order to analyse the PD data in both the time- and frequency-domain. The analysis of the measured data revealed PD characteristics of the test specimen used for the measurements. The designed CM is used for the detection of PD activity within electrical cables and in combination with other techniques, may be used for complete CM of electrical cables. The experimental setup which was used to take practical PD measurements adds another dimension to the work presented in this dissertation. / MIng (Electrical and Electronic Engineering), North-West University, Potchefstroom Campus, 2015