Periodic Reporting for period 4 - IN2SMART (Intelligent Innovative Smart Maintenance of Assets by integRated Technologies)
Période du rapport: 2019-01-01 au 2019-10-31
IN2SMART was born in the context of a growing demand for a step change in asset management to be delivered through innovative technologies, new economic possibilities, and enhanced legislative standards in the rail sector. It wants to contribute to create new and optimised strategies, frameworks, processes and methodologies, tools, products and systems for the implementation of a step change in risk based, prescriptive and holistic asset management in the rail sector. To do this the project is structured in the three former Technological Demonstrators:
• TD3.7 Railway Information Measuring and Monitoring System (RIMMS) that focuses on asset status data collection (measuring and monitoring), processing and data aggregation producing data and information on the status of assets;
• TD3.6 Dynamic Railway Information Management System (DRIMS) that focuses on interfaces with external systems; maintenance-related data management and data mining and data analytics; asset degradation modelling covering both degradation modelling driven by data and domain knowledge and the enhancement of existing models using data/new insights;
• TD3.8 Intelligent Asset Management Strategies (IAMS) that concentrates on decision making (based also but not only on TD3.6 input); validation and implementation of degradation models based on the combination of traditional and data driven degradation models and embedding them in the operational maintenance process based upon domain knowledge; system modelling; strategies and human decision support; automated execution of work.
In particular, new predictive approaches could make possible for operators to be well aware of Asset Management and maintenance needs before failure.
Therefore, an intelligent infrastructure should be equipped not only with a range of static and mobile autonomous monitoring technologies/sensors, which are able to communicate with each other, but also with tools and predictive algorithms, degradation laws and models to provide a running commentary of the infrastructure current and predicted status to achieve a reliable railway infrastructure.
In this context, the IN2SMART project aimed at contributing to the development of an Intelligent Asset Management System (IAMS), identifying the main ‘building blocks’ and their interactions, showing how the use of big data and predictive analytical techniques could foster the optimization of Asset Management and the prolongation of asset lifetime.
• TD3.7 Railway Information Measuring and Monitoring System (RIMMS) that focuses on asset status data collection (measuring and monitoring), processing and data aggregation producing data and information on the status of assets;
• TD3.6 Dynamic Railway Information Management System (DRIMS) that focuses on interfaces with external systems; maintenance-related data management and data mining and data analytics; asset degradation modelling covering both degradation modelling driven by data and domain knowledge and the enhancement of existing models using data/new insights;
• TD3.8 Intelligent Asset Management Strategies (IAMS) that concentrates on decision making (based also but not only on TD3.6 input); validation and implementation of degradation models based on the combination of traditional and data driven degradation models and embedding them in the operational maintenance process based upon domain knowledge; system modelling; strategies and human decision support; automated execution of work.
In particular, new predictive approaches could make possible for operators to be well aware of Asset Management and maintenance needs before failure.
Therefore, an intelligent infrastructure should be equipped not only with a range of static and mobile autonomous monitoring technologies/sensors, which are able to communicate with each other, but also with tools and predictive algorithms, degradation laws and models to provide a running commentary of the infrastructure current and predicted status to achieve a reliable railway infrastructure.
In this context, the IN2SMART project aimed at contributing to the development of an Intelligent Asset Management System (IAMS), identifying the main ‘building blocks’ and their interactions, showing how the use of big data and predictive analytical techniques could foster the optimization of Asset Management and the prolongation of asset lifetime.
The architecture of the IAMS has been defined in line with the ISO55000 (ISO, 2014) and the UIC Guidelines for asset management in rail sector (UIC, 2016). In particular, the classification between SAMP (Strategic Asset Management Plan), AMP (Asset Management Plan) and IAMP (Implementation of the Asset Management Plan) levels, identified by the ISO55000, is taken into account.
The Intelligent Asset Management System was based on five main layers :
• IAMS Data Collection: Identification and collection of all the information (Static and Dynamic) that have to be extracted for the proper monitoring of the involved assets/systems. This includes the understanding of different data formats of logs coming from such systems, which should be received through ad hoc or native interfaces.
• IAMS Data Platform: Creation of a data platform to collect, clean, store and manage the data coming from the field. This platform is highly scalable, potentially geographically distributed, flexible and able to work with structured and unstructured data to be used as a base for further data analysis.
• IAMS Data Analysis: Design and implementation, for each identified system/asset to be managed by the IAMS, of methodologies and analytic solutions for the assets status assessment and future status prediction (predictive maintenance).
• IAMS Planning and Decision Support Systems (DSS): Design and implementation of optimization techniques aimed at supporting infrastructure managers and operators in making decisions on the prioritizations of interventions, guaranteeing the achievement of the desired targets of rail service availability, reliability and efficiency. Management activities are planned taking into account the predicted status of the asset and the criticality of the asset, that is, the impact that its failure would have on the entire system.
• IAMS HMI: Creation of a customizable HMI able to support the asset management, visualizing concise information for each system/asset and related IAMS functionalities and the results coming from analytics.
The innovative asset management system had the following key features:
• Integration layer that allows communication between different data formats.
• Diagnostics and anomaly detection techniques that enable automatic anomaly detection and provide alarms.
• Tools and models for predictive analytics that are able to extract information using the heterogeneous data from the field from many sources.
• RAMS and integration/risk modules that allow to assess the impact of an asset failure on the entire system performance, in terms of service disruptions, evaluating asset criticalities and integrating the outputs of the data analytics in the decision support.
• Planning functionalities, based on optimization techniques that aim at scheduling efficiently Asset Management interventions considering constraints, such as crew availability, and goals such as cost-efficiency, system reliability and availability, etc..
The decision support system contributes to the prevention of costly failures and supports operational Asset Management and maintenance decision making at strategic, tactical and operational levels (SAMP, AMP, IAMP)
The Intelligent Asset Management System was based on five main layers :
• IAMS Data Collection: Identification and collection of all the information (Static and Dynamic) that have to be extracted for the proper monitoring of the involved assets/systems. This includes the understanding of different data formats of logs coming from such systems, which should be received through ad hoc or native interfaces.
• IAMS Data Platform: Creation of a data platform to collect, clean, store and manage the data coming from the field. This platform is highly scalable, potentially geographically distributed, flexible and able to work with structured and unstructured data to be used as a base for further data analysis.
• IAMS Data Analysis: Design and implementation, for each identified system/asset to be managed by the IAMS, of methodologies and analytic solutions for the assets status assessment and future status prediction (predictive maintenance).
• IAMS Planning and Decision Support Systems (DSS): Design and implementation of optimization techniques aimed at supporting infrastructure managers and operators in making decisions on the prioritizations of interventions, guaranteeing the achievement of the desired targets of rail service availability, reliability and efficiency. Management activities are planned taking into account the predicted status of the asset and the criticality of the asset, that is, the impact that its failure would have on the entire system.
• IAMS HMI: Creation of a customizable HMI able to support the asset management, visualizing concise information for each system/asset and related IAMS functionalities and the results coming from analytics.
The innovative asset management system had the following key features:
• Integration layer that allows communication between different data formats.
• Diagnostics and anomaly detection techniques that enable automatic anomaly detection and provide alarms.
• Tools and models for predictive analytics that are able to extract information using the heterogeneous data from the field from many sources.
• RAMS and integration/risk modules that allow to assess the impact of an asset failure on the entire system performance, in terms of service disruptions, evaluating asset criticalities and integrating the outputs of the data analytics in the decision support.
• Planning functionalities, based on optimization techniques that aim at scheduling efficiently Asset Management interventions considering constraints, such as crew availability, and goals such as cost-efficiency, system reliability and availability, etc..
The decision support system contributes to the prevention of costly failures and supports operational Asset Management and maintenance decision making at strategic, tactical and operational levels (SAMP, AMP, IAMP)
in terms of progress beyond the state of art the the IAMS finalization has included or will include the in field validation of monitoring solutions such as unmanned autonomous vehicles; the validation of an open standard interface for maintenance applications; the validation of analytic tools for automatic detection of anomalies and prediction of railway assets decay; the implementation of In-Lab demonstrators of the Data Analytics Architecture; the in field validation of decision support tools for long, mid- and short-term maintenance planning; the in field demonstration of maintenance tools, using technology applicable for the next generation robot platform. Finally, the decision support system applications could be extended by including other assets and new input data, but also by developing added-value functionalities. All the activities are expected to finish with technologies demonstrated/validated in a TRL6/7 environment as a continuation of the work already conducted in IN2SMART and that will be furtherly conducted until in IN2SMART2 project.
In fact the entire project scope is to aim towards an intelligent asset management systems (IAMS) according to ISO 55000; taking into consideration that IN2SMART was the first step only, aiming to reach TRL4-5 results.
In this view some tangible progress beyond the state of art were targeted inside the RIMMS WPs, whilst they were clearly premature for DRIMS and IAMS WPs.
As a logic view, the continuity with IN2SMART2, started at 1st December 2019 will allow the completion of the expected potential socio-economic impact.
In fact the entire project scope is to aim towards an intelligent asset management systems (IAMS) according to ISO 55000; taking into consideration that IN2SMART was the first step only, aiming to reach TRL4-5 results.
In this view some tangible progress beyond the state of art were targeted inside the RIMMS WPs, whilst they were clearly premature for DRIMS and IAMS WPs.
As a logic view, the continuity with IN2SMART2, started at 1st December 2019 will allow the completion of the expected potential socio-economic impact.