Open System Architecture For Condition Based Maintenance Research Articles

Prognostic and Diagnostic Coupling Framework Based on OSA-CBM strategy for Photovoltaic Generators

This article proposes a prognostic and diagnostic coupling framework based on the OSA-CBM (Open System Architecture for Condition Based Maintenance) for photovoltaic generators (PVG). At First, this work presents some PVGs performance degradation studies and the main degradation indicators. We select the Corrected performance ratio (CPR) as degradation indicator associated with the Loess data analysis method to avoid aberrations and errors from acquisition system. Then, the main methods of coupling diagnostic and prognostic processes are explained: Watch Dog, Prognostic Enhancements to Diagnosis Systems (PEDS), Integrated Predictive Maintenance Systems (SIMP) and OSA-CBM. This last strategy with its seven specialized layers permits the interoperability of both processes. The monitoring system provides health indicators of PVGs and results are returned to human operator. The annual reduction rate of the CPR and reduction rate (Rd), allows us controlling the proposed coupling framework. This approach is validated with experimental data collected on four photovoltaic installations from the IEA PVPS Task13 database.

A Generalised Methodology for the Diagnosis of Aircraft Systems

An aircraft is made up of a number of complicated systems which work in harmony to ensure safe and trouble-free flight. In order to maintain such a platform, many diagnostic and prognostic techniques have been suggested, mostly aimed at components but some at the system level. Together these form a patchwork approach to the overall problem of efficiently informing aircraft maintenance to the Original Equipment Manufacturers, the operators /airlines, and the Maintenance, Repair, and Overhaul organisations. It involves these organisations having to support several different approaches to aircraft health management, and is therefore inefficient and costly. In the current work, a streamlined methodology is put forward. This is based on OSA-CBM (Open System Architecture for Condition Based Maintenance) and can be applied to any aircraft system. Integral with this is the use of mRMR (minimum redundancy maximum relevance) for feature selection, the resulting symptom vector being used for fault diagnosis. This approach is demonstrated on three test cases: the engine, the environmental control system, and the fuel system. In each case, the digital twin setup, simulation conditions for healthy and faulty scenarios, a methodology based on OSA-CBM up to diagnostics are detailed. Diagnostics is carried out for each system in turn, using four machine learning supervised algorithms. The best performing algorithm for each system will then subsequently be used in a vehicle level reasoner called FAVER (A Framework for Aerospace Vehicle Reasoning), which requires these system diagnoses as a starting point for vehicle reasoning and fault ambiguity resolution.

Railway Defender Kill Chain to Predict and Detect Cyber-Attacks

Most organizations focus on intrusion prevention technologies, with less emphasis on prediction and detection. This research looks at prediction and detection in the railway industry. It uses an extended cyber kill chain (CKC) model and an industrial control system (ICS) cyber kill chain for detection and proposes predictive technologies that will help railway organizations predict and recover from cyber-attacks. The extended CKC model consists of both internal and external cyber kill chain; breaking the chain at an early stage will help the defender stop the adversary’s malicious actions. This research incorporates an OSA (open system architecture) for railways with the railway cybersecurity OSA-CBM (open system architecture for condition-based maintenance) architecture. The railway cybersecurity OSACBM architecture consists of eight layers; cybersecurity information moves from the initial level of data acquisition to data processing, data analysis, incident detection, incident assessment, incident prognostics, decision support, and visualization. The main objective of the research is to predict, prevent, detect, and respond to cyber-attacks early in the CKC by using defensive controls called the Railway Defender Kill Chain (RDKC). The contributions of the research are as follows. First, it adapts and modifies the railway cybersecurity OSA-CBM architecture for railways. Second, it adapts the cyber kill chain model for the railway. Third, it introduces the Railway Defender Kill Chain. Fourth, it presents examples of cyber-attack scenarios in the railway system.

Research on the health management of an automatic magazine control system to the naval gun

According to the problems of low maintenance efficiency and high cost for traditional regular maintenance and after-the-fact maintenance methods, PHM technology is introduced to improve the success rate of the system operation, extend the service life, and reduce maintenance difficulty and cost. Aiming at the overall situation of the automatic magazine control system of a large-caliber gun weapon, a new health management system based on a data-driven method is proposed. Establishing a PHM model applied to automatic magazine control system by using the structure of open system architecture for condition-based Maintenance (OSA-CBM); the prediction and evaluation function of PHM system is studied with an example of transfer servo drive system; the prediction model based on BP neural network is established to predict the health parameters of the automatic magazine control system. Then the health state of system is evaluated according to the prediction result and the function is verified by simulation. The simulation results show this BP neural network model is applicable for the parameter prediction of the prediction and evaluation module of the automatic magazine PHM system. The prediction accuracy is over 90%, and the model has a good applicability.

Integrated System of Predictive Maintenance and Operation of Eletronorte Based on Expert System

Maintenance based on condition and diagnosis technology has a relevant function in Power Electrical System's reliability. This paper proposes the methodological development and computational implementation of a system capable of failure diagnosis on electrical generation assets in order to aid the maintenance crew and the operation at the Coaracy Nunes hydropower plant, located in the Amapa state, in the decision making related with executions of operation and maintenance actions to minimize the incipient issues before they actually occur. The proposed methodology is based in the OSA-CBM (Open System Architecture for Condition-Based Maintenance) model to structure the system’s knowledge base, in addition to implement fuzzy production rules to diagnosis of more complex failures. A case study was realized at the referred plant, showing in the results that the proposed system has a big potential on failure detection. Predictive maintenance and pattern recognition are technological enablers of Industry 4.0.

A Functional Architecture of Prognostics and Health Management using a Systems Engineering Approach

Prognostic and Health Management (PHM) describes a set of capabilities that enable effective and efficient approaches towards data analysis for fault diagnostics and failure prognostics. This can support decision making related to health management, sustainment and operation of critical systems, such as aviation systems. As a result of the rapidly growing interest in PHM, a substantial amount of research proposes and discusses PHM frameworks and system architectures. Many research efforts regarding PHM frameworks focus on technical aspects, such as techniques associated with big data, cloud-based distribution or open facilities. Several papers propose specific PHM system architectures based on different frameworks. In addition, several authors address the derivation of PHM system architectures from system requirements (related to functions, behaviours, structures) using a systems engineering perspective. However, further interpretations of PHM system architecture derived from requirements in functional view are lacking. Moreover, the PHM system operates as a system of systems as it results from the combination of aviation systems, airline operational systems, and other ground health management hosting systems. In both research and industry, these systems are discussed and designed independently, whereas they need to be integrated to offer monitoring functions and services. Research of PHM architecture allowing communication and integration with the various contributing systems is lacking. To address these gaps, this research outlines an architecture design methodology incorporating a functional view from a systems engineering perspective. In addition, it proposes a functional architecture for PHM system as the application of the methodology. This proposed architecture is derived from associated functions and requirements to identify the functional elements, system boundary and the external/internal interactions of PHM system, to ensure the traceability and efficiency of architecture design. It also has compatibility and interoperability to integrate with the various systems, due to its compliance with the standard of Open System Architecture for Condition-Based Maintenance (OSA-CBM). A Case Study is conducted to verify the functional hierarchy and interactions and to demonstrate the compatibility and applicability through a compliance matrix. Furthermore, architecture models are established using System Modeling Language (SysML) through structural diagrams to represent the static structure and interactions. These models also sustain the integration with a variety of other information or management systems that together enable an organization to operate efficiently and competitively using health monitoring services through OSA-CBM.

Adoption of MEMS technology in e-maintenance systems for rotating machinery

Microelectromechanical systems (MEMS)-based sensing networks with on-board signal processing capabilities are becoming very attractive for monitoring the condition of rotating and static equipment. Their advantages in cost and size are an important factor for deployment in a new generation of maintenance called e-maintenance. In this paper, an intelligent monitoring system for e-maintenance (IMSEM) was developed using MEMS accelerometers, a low-power microprocessor and a wireless communication module. The system has a compatible framework and interface with open system architecture for condition-based maintenance (OSA-CBM). It integrates OSA-CBM-defined functions, including a sensing module, signal processing, condition monitoring and health assessment. Thus, the developed system successfully reduced the monitoring complexity and communication overhead with human operators. The performance of IMSEM is evaluated by carrying out fault diagnostics on the rotating unbalance of a mechanical shaft driven by a direct current (DC) motor with varying load and speed. Five statistical features were calculated for 63 vibration datasets. 25 datasets were used to train a support vector machine, with a linear kernel, and the other 38 sets were used for binary classification. About 94.7% of unknown conditions were successfully classified as healthy/unhealthy based on all features, which was improved to 100% using the best three features. This has demonstrated the capability of the developed system in detecting faults and the severity of rotor unbalance, based on ISO 1940-1:2003.

Implementing MIMOSA Standard

A common challenge to Prognostic Health Management (PHM) systems is the management of data across different organizations based on a standardized format and meaning. The Open System Architecture for Condition-based Maintenance (OSA-CBM) and the Open System Architecture for Enterprise Application Integration (OSA-EAI) are complementary reference architectures for domain-independent asset and condition data management. In previous papers, we reported on our experiences with implementing a data integration layer based on these two architectures. In this paper, we report on our experience implementing code generators for binary OSA-CBM and OSA-EAI Tech-CDE (Compound Document Exchange), and the utilization of the resulting components within the OMAHA project. OMAHA aims towards an overall management architecture for health analysis, incorporating manufacturers, operators and maintainers of fleets of aircraft.The OSA-CBM standard specifies a message structure but leaves the assembly and disassembly of OSA-CBM data up to the implementor. Our solution is a builder/reader Application Programming Interface (API) for a binary OSA-CBM message codec which we have implemented under the constraints of a real-time computing environment. The required C code is automatically generated from the provided technical documentation for OSA-CBM. We discuss the properties of the resulting codec and point out future improvements for the OSA-CBM binary protocol to improve consistency and to add the capability of streaming. Using the same generative approach we have implemented a code generator for a Tech-CDE-compliant middleware system, consisting ofclient libraries (currently C++ and Java), a network layer, a server portion, and a database backend. Analogously to OSA-CBM, the code generator processes the documentation provided for Tech-CDE, creating both productive and testing code. We discuss the properties of the resulting system, report specific limitations of the Tech-CDE protocol and suggest mitigations. The paper concludes with an experience report from utilizing our work in the OMAHA project. While Tech-CDE was generally found sufficient, we identified areas of improvement, including protocol properties and entity coverage. We were able to make customizations using our generative coding approach and present these as suggestions for future standard extensions.

A Bayesian paradigm for aircraft operational capability assessment and improved fault diagnostics

In recent years, Bayesian networks have been drawing attention of the industrial and research community especially in the field of diagnostics for the reasoning capabilities they offer under conditions of uncertainty.Given the system of interest, a Bayesian network represents a graphical model of the system itself, in which the different players are linked to each other through probabilistic and causal relations. If the model is queried with appropriate statistical techniques, the whole approach can present several advantages over other data analysis methods. Among the others: 1) the approach can provide outputs even if some entries to the model are missing, due to the above mentioned dependencies between the players of the system; 2) the approach represents an ideal environment to include prior knowledge during the building up of the model, given the causal and probabilistic semantics; 3) a Bayesian network provides the possibility to learn causal relationships and gives therefore the possibility to improve the domain knowledge.Airbus Defence and Space has been working on improving the aircraft diagnostics capabilities at component, sub-system and system level in terms of fault detection and isolation. The focus has been also to develop means for reasoning about the remaining operational and functional capabilities of the aircraft.The initial outcomes have been tested on a simulation platform featuring a Data Acquisition Processing Unit, various computing nodes, on which the different aircraft systems (like the fuel system, the hydraulic system, the actuation systems, etc…) run. The data communication architecture of the platform is based on OSA-CBM (Open System Architecture for Condition-Based Maintenance).Initial objectives of the project are: 1) to demonstrate the feasibility of integration of the concept within the above described simulation framework; 2) to develop means to allow an easy and structured translation of the system engineer knowledge in terms of a Bayesian network with associated conditional probabilities; 3) to provide a modular architecture for the concept facilitating effective coordination between the development-departments and efficient development and maintenance of the software and 4) to prove the scalability of the concept (i.e. applicability to systems of different sizes and reasoning on different levels from component to system level).The candidate systems selected for the proof of concept are the fuel and the hydraulic systems of a generic aircraft. The results obtained so far look promising with respect to the above mentioned objectives of the project.

Evolving the Data Management Backbone: Binary OSA-CBM and Code Generation for OSA-EAI

Integrated system health monitoring and management (ISHM) is a field of research and development where both academia and industry is highly focused on. Airbus Defence & Space has recognized that simulation is a key capability for developing ISHM technologies and is therefore in the process of developing a comprehensive simulation framework in that area. One significant building block is to invite 1st class technology providers, e.g. Universities and SMIs, to provide innovative technologies and support their integration into the simulation framework. This paper is a joint presentation of Airbus Defence & Space and Linova Software GmbH, an Airbus Defence & Space preferred software provider. The Open System Architecture for Condition-based Maintenance (OSA-CBM) and Open System Architecture for Enterprise Application Integration (OSA-EAI) are complementary reference architectures and represent an emerging standard for application domain-independent asset and condition data management. The architectures address several challenges in building Prognostic Health Management (PHM) systems, which are commonly composed of disparate and distributed hard- and software components. Therefore, a common challenge to PHM systems is to be confronted with vast amounts of data which are exchanged over a heterogeneous collection of communication channels. Any such system’s success depends upon an open, uniform, and performance-optimized solution for data management. A solution that includes: data definition, data communication, and data storage. We will follow up on previous work and report on our experiences from implementing our second generation data management backbone based on binary OSA-CBM transmission. We also aim at implementing a fully OSA-EAI compliant database. We confirmed the general feasibility of OSA-CBM and OSA-EAI by previous work. We have now migrated our data management backbone to the current release of OSA-CBM, which includes a standard binary transportation format. We report on our experience from implementing this format and discuss issues regarding message handling and Meta data overhead. In previous work we used a simplified and stripped-down implementation of OSA-EAI and our current goal was to be fully compliant with the OSA-EAI standard. In order to reach this goal, we have created a code generator which receives OSA-EAI-provided documentation artifacts as input. It produces compileable source code for a Java-based 3-tier OSA-EAI information system. We have identified issues with the OSA-EAI standard regarding completeness and handling, which we discuss, and suggest means for mitigation or enhancements to the standard. To underline the feasibility of our solutions, we provide empirical evidence drawn from our work. The conclusion is a summary of our experience and the direction of future work in the area of PHM system design for aircraft maintenance. In total, our contribution to the community is best seen from a practitioner’s perspective.

Data Management Backbone for Embedded and PC-based Systems Using OSA-CBM and OSA-EAI

Cassidian is in the process of developing a comprehensive simulation framework for integrated system health monitoring and management research and development. One significant building block is to invite 1st class technology providers, e.g. Universities and SMIs, to provide innovative technologies and support their integration into the simulation framework. This paper is a joint presentation of Cassidian and Linova Software GmbH, a Cassidian preferred software provider.Prognostic Health Management (PHM) systems are commonly composed of disparate and distributed hard- and software components. Further, these components exchange vast amounts of data over a heterogeneous collection of communication channels. Any such system’s success depends upon an open, uniform, and performance-optimized solution for data management. A solution that includes: data definition, data communication, and data storage. The Open System Architecture for Condition-based Maintenance (OSA-CBM) and Open System Architecture for Enterprise Application Integration (OSA-EAI) are complementary reference architectures and represent an emerging standard for application domain-independent asset and condition data management. Herein, we will report on our experiences while implementing a data management backbone based on OSA-CBM and OSA-EAI for a simulation environment supporting PHM systems in the aerospace domain. Our work encompasses both airborne embedded systems and ground-based PC systems. While we can generally confirm the feasibility of OSA-CBM and OSA-EAI, we found several implementation recommendations unsuited to real-time operating conditions. To address these issues, we propose work towards standardizing non-XML-based transportation formats for OSA-CBM data packets. Further, we discovered issues specific to implementing the OSA-EAI data model in the aerospace domain. These issues drove our proposal to extend the OSA-EAI database model, where we seek to optimize its usability for analytical tasks. To underline the feasibility of our solutions, we provide empirical evidence drawn from our work. The conclusion is a summary of our experience and the direction of future work in the area of PHM system design for aircraft maintenance. In total, our contribution to the community is best seen from a practitioner’s perspective. We aim to establish best practices for and contribute to the evolution of OSA-CBM and OSA-EAI.