Enhancing Reliability-Centered Maintenance (RCM) with OSIsoft PI System and Smart RDM Integration 

Marek Zając


Reliability-Centered Maintenance (RCM) is a widely implemented process to determine the most effective and cost-efficient timing for equipment maintenance. The OSIsoft PI system is a data infrastructure platform that enables real-time data collection, storage, and analysis. Maintenance strategies and equipment reliability can be improved by integrating with the RCM strategy. While real-time data alone may not provide a complete picture of risk, it can still be used to calculate certain aspects of risk within the context of RCM.  

Real-time data can be used to establish threshold values or alarm limits for various parameters related to equipment health. These thresholds indicate the safe operating range or conditions of the equipment. If the real-time data exceeds these limits, it can trigger alarms or alerts, indicating a potential risk. By monitoring the data against these thresholds, the system can identify deviations and help mitigate risks associated with abnormal operating conditions. Real-time data provides valuable information on the current state of the equipment. Deviations from normal operating conditions can be identified by continuously monitoring parameters such as temperatures, pressures, vibration levels, and flow rates. These deviations may indicate potential risks and can be analyzed to assess the severity and possible consequences of the risk.  

Real-time data can be analyzed over time to identify trends and patterns. By examining the historical trends of equipment parameters, maintenance personnel can identify degradation or changes in performance. Sudden changes or deteriorating trends can indicate potential risks, which can be further investigated and evaluated. Real historical data can be utilized in conjunction with predictive analytics techniques to assess risk. Predictive models trained on historical data can use real-time data as input to predict the probability and likelihood of future failures or critical events. Considering the real-time data in these models, the risk associated with potential losses can be quantified and prioritized based on their impact on equipment performance and overall plant operations.  

While real-time data is valuable, the expertise and judgment of maintenance personnel are equally important in assessing risk. Real-time data provides a foundation for decision-making, but experienced professionals can interpret and contextualize the data based on their knowledge of the equipment and industry standards. They can integrate real-time data with other relevant information, such as historical failure data, maintenance records, and environmental factors, to calculate risk and make informed decisions regarding maintenance actions.  

It’s important to note that while real-time data is valuable for assessing risk, a comprehensive risk assessment within RCM also considers other factors, such as the criticality of the equipment, the consequences of failure, and the effectiveness of potential maintenance strategies. Real-time data serves as a critical input in the risk assessment process, helping to identify and prioritize potential risks and guide maintenance decisions.  

The Role of OSIsoft PI System and Smart RDM Integration   

Integrating the OSIsoft PI System with the Smart RDM platform supports the Reliability-Centered Maintenance (RCM) procedure by providing robust data management, analytics capabilities, and decision support tools throughout the different steps. Here’s how the integration supports each stage of the RCM procedure:  

Historical Data Collection and Building Data Context (Steps 1-3): The OSIsoft PI System, specifically the PI Asset Framework (PI AF), plays a crucial role in this phase. PI AF allows for creating a structured hierarchy or “tree” based on equipment or production process dependencies. It provides a contextual framework for assets, allowing organizations to efficiently organize and relate data elements. PI AF can integrate data from multiple sources and external relational databases, ensuring data integrity and enabling advanced operations without external analytical tools. The data collected and organized within PI AF is the foundation for historical data analysis and understanding asset functions.  

Failure Mode and Effects Analysis (FMEA) (Step 4): The Smart RDM platform’s Big Data module, combined with data from the PI System, supports the FMEA process. By leveraging historical data, real-time monitoring, and advanced analytics capabilities, organizations can systematically evaluate and prioritize failure modes based on their impact on safety, production, and costs. The integration allows for a comprehensive analysis of failure modes and their effects on asset performance.  

Criticality Analysis (Step 5): Integrating the PI System and the Smart RDM platform enables accurate criticality analysis. The data analytics capabilities of the Smart RDM platform, combined with the PI System’s contextual data, support asset and failure mode criticality assessment. Organizations can evaluate the consequences, likelihood, and severity of failures, enhancing the accuracy of criticality assessments and prioritization.  

Maintenance Strategy Selection (Step 6): The Smart RDM platform provides decision support tools to assist organizations in selecting the most suitable maintenance strategies for each asset based on their criticality and failure modes. Organizations can make informed decisions on maintenance approaches by considering cost-effectiveness, safety, and reliability. The integration with the PI System ensures that historical and real-time data are incorporated into the decision-making process.  

Maintenance Ranking Creation and Task Selection (Steps 7 and 8): The integration allows organizations to comprehensively rank maintenance tasks based on criticality, resource availability, and other relevant factors. Organizations can prioritize maintenance tasks by combining data from the PI System and the Smart RDM platform. The Smart RDM platform’s other modules support maintenance task selection by considering resource availability, skill requirements, and task dependencies, optimizing the maintenance schedule, and ensuring efficient execution.  

Maintenance Optimization, Performance Monitoring, and Feedback (Steps 9-11): Integrating the PI System with the Smart RDM platform facilitates maintenance optimization, real-time monitoring, and performance evaluation. By leveraging real-time data from the PI System, organizations can continuously monitor asset performance, identify potential issues, and optimize maintenance activities accordingly. The Smart RDM platform provides performance metrics, KPIs, and feedback mechanisms, enabling organizations to measure their maintenance activities’ impact, identify improvement areas, and make data-driven decisions.  


This article introduces Reliability Centered Maintenance (RCM) as a process for determining optimal maintenance timing and improving equipment reliability. It highlights the advantages of implementing RCM, which is historically known as a process, that contributed to groundbreaking discoveries in the aviation industry. The RCM procedure is explained, encompassing fundamental questions that guide the methodology. The integration of the OSIsoft PI System with the Smart RDM platform is then discussed, illustrating how each stage of the RCM procedure is supported. The article highlights the role of the PI Asset Framework (PI AF) in historical data collection and building data context, the Smart RDM platform’s Big Data module in failure mode analysis (FMEA), and the integration’s impact on criticality analysis, maintenance strategy selection, ranking creation, task selection, maintenance optimization, performance monitoring, and feedback. Integrating these systems enhances data management, analytics capabilities, and decision support tools, ultimately improving maintenance outcomes and operational excellence in organizations implementing RCM.