Optimizing asset management through automated workflows

Introduction

In the organizational world, assets are one of the most important aspects, because they are widely related to production and business performance. Therefore, it is essential that these resources are in good condition and can function optimally. That’s where the term “asset management” comes from; which has been subject to evolution thanks to the implementation of automated workflows.

While asset management seeks to guarantee the integrity and correct functioning of equipment, workflow automation aims to optimize the processes and phases behind resource maintenance strategies. Without a doubt, the combination of these two practices can bring about improvements in production, efficiency and operability. For this reason, in the following article we will learn about the impact of automated workflows on the management of industrial assets.

What is workflow automation?

It refers to the application of specialized software for the efficient management of tasks, documents and data, establishing a logical and predictable sequence of information. It is a technical approach used in the business context to optimize processes and improve operational efficiency. This concept arises in response to today’s dynamic business environment, where organizations continually seek methods to streamline their operations, and one of the key areas to achieve substantial improvements is workflow management.

Traditional manual workflows, characterized by significant time consumption, error-proneness, and the generation of potential bottlenecks that affect productivity, can experience significant improvements through automation. Specialized technologies and systems to replace or improve manual tasks, reducing time spent on operations, minimizing errors and eliminating obstacles that may affect the overall efficiency of the process.

In short, workflow automation represents a key strategy for continuous process improvement, allowing organizations to adapt more agilely to the challenges and changing demands of the business environment.

Automation tools

Automated control systems (SCADA)

They are computer systems that collect, process and control data from industrial processes remotely, focusing on the specialized application of software to efficiently manage tasks, documents and data, establishing logical and predictable sequences of information. This technical approach, in the business field, optimizes processes and increases operational efficiency ¹ .

Its implementation arises as a response to the dynamic industrial environment, where agility is key, replacing manual workflows. This technology can reduce operating times, minimize errors and eliminate obstacles, allowing you to adapt agilely to changing challenges. For this reason, it is one of the main options in risk management optimization processes.

Computer Aided Maintenance Systems (CMMS)

It is a comprehensive software tool designed to centralize and optimize information and processes related to asset maintenance in various industries ² , including manufacturing, oil, gas, energy, construction and transportation. Its main function is to facilitate the efficient management of physical assets, such as vehicles, machinery and infrastructure, by centralizing data in a solid database.

This system operates around a database that organizes critical information about assets, equipment, materials and associated resources. Its key functions include labor and resource management, detailed asset recording, complete work order management with automation capabilities, preventive maintenance based on time, usage or events, materials and inventory management, and generation of detailed reporting, analysis and auditing to support informed decision making and continuous optimization of maintenance processes.

Automated fault diagnosis systems

They are based on the use of Artificial Intelligence (AI) to improve efficiency and precision in detecting problems in industrial processes. The way to achieve this is through the integration of AI algorithms with traditional methods. In this way, these systems speed up the identification of failures, reducing downtime and increasing productivity.

One of the biggest advantages of using AI-automated fault diagnosis systems is their ability to handle large volumes of data and recognize complex patterns. Using machine learning algorithms, these systems analyze historical data and sensor readings in real time , allowing early detection of deviations and facilitating the creation of predictive models to implement proactive maintenance strategies.

IoT Sensors

Sensors that implement IoT (Internet of Things) technologies in the context of workflow automation facilitate the collection of real-time data on the performance, status and location of assets ³ . These internet-connected devices detect key variables such as vibration, temperature or humidity, providing valuable information for making informed decisions about asset management.

The ability to monitor the status of assets in real time allows for early detection of changes and deterioration, facilitating the development of preventive actions that reduce the risk of critical failures, thus reducing downtime and maintenance costs. The integration of IoT sensors represents a way of optimizing asset management by improving operational efficiency and the strategic decision-making process.

Benefits of automated workflows in asset management

• Production Optimization: By implementing automated management systems, effective optimization of oil production is achieved by reducing unplanned downtime. These systems not only minimize costly outages, but also maximize the integrity of assets and wells. In addition, automation contributes to greater reservoir recovery and improves the overall performance of the oil process.

• Damage cost reduction: The primary purpose of asset management is to ensure the integrity and proper functioning of industrial equipment. Thanks to the automation of workflows, there are various ways to mitigate possible problems and damage that assets may suffer, resulting in the reduction of costs related to repairs, corrective maintenance and machinery changes.

• Development of predictive analytics: Through data such as performance records, histories, and values ​​captured by sensors in real time, automated systems can generate predictive analytics; Therefore, failures can be anticipated, deficiencies detected and maintenance strategies established, generating as a result the optimization of asset management that is being implemented in the facilities.

• Improved decision making: Automation allows for greater precision in the analysis of valuable data, eliminating the possibility of human error, and also streamlines the analysis process, allowing for faster and more accurate decision making.

• Elimination of obsolete processes and practices: With the implementation of an automation platform, dispersed processes can be consolidated and centralized. This strategy enables efficient data exchange between platforms, eliminating redundant tasks and creating a comprehensive view of incoming data flows, optimizing core operations and tasks.

Success stories

Aker BP

Considering downtime is costly for oil platforms, Aker BP, in collaboration with Spark Cognition, successfully implemented Machine Learning (ML) to optimize asset management on its Tambar unmanned platform. Focusing on preventing failures in a critical multiphase pump (equipment that caused various downtimes), an AI-based predictive maintenance solution was developed.

Using normal behavior models of the critical multiphase pump, the software would alert detected deviations, anticipating possible pump failures, and also identifying the causes of the problems.

For six months, this solution allowed early intervention of operators, avoiding failures that had previously generated production losses of more than 10 million dollars ⁴ . The expansion of this technology called SparkPredict to the entire Aker BP fleet demonstrates the scope of these systems in improving productivity and efficiency in offshore environments.

shell

In the quest to improve the management of its assets, Shell decided to implement machine learning (ML) models, especially for predictive maintenance of control valves. Previously, the maintenance strategies they executed were based on time-based or failure-based approaches, leading to inefficient practices. Physics-based models improved condition monitoring, but assets demanded improved reliability, so they decided to turn to workflow automation through Machine Learning ⁵ .

Shell’s instrumentation engineering team, in collaboration with Delft University of Technology and Shell’s digital team, explored the role of artificial intelligence in early detection of control valve problems. ML models were developed to analyze the massive data packets generated by each asset, allowing the identification of anomalies and triggering alerts for proactive maintenance.

A refinery in the Netherlands successfully implemented the new predictive maintenance model, detecting 65 control valve problems that traditional methods would have missed. This ML-driven approach improved reliability, reducing downtime and marking significant progress in optimizing Shell’s asset management.

The evolution of asset management

Due to constant development and innovations in industrial practices, the complexity of these operations may increase. On the other hand, the drive to have optimal levels of competitiveness has led companies to experience an evolution in asset management.

Despite the changes and innovations that may be developed at the industrial level, having good asset management is a fundamental aspect for good organizational functioning. Focusing more on assets and ensuring their optimal condition and functioning; which translates into an increase in productivity and efficiency.

In the coming years, a growing number of companies in the oil and gas sector will incorporate automation technologies. In fact, the future of these industries could lie in the convergence of various technologies, including machine learning, where those companies that adapt quickly will improve the optimization of their resources and obtain a more detailed view of their progress.

Conclusion

Optimizing asset management through automated workflows represents a critical step towards operational efficiency and informed decision making across various industries. Through this tool, organizations can streamline processes, reduce errors and maximize the useful life of their assets.

This approach not only improves productivity, but also contributes to cost reduction and the ability to quickly adapt to changes in the business environment. In an increasingly technology-driven world, the effective implementation of automated workflows is positioned as an essential element to achieve optimal performance in asset management.

References

1. CEIINC. (sf). What is a SCADA? Retrieved January 17, 2024, from https://ceiinc.co/que-es-un-scada/
2. IBM. (sf). What is a CMMS (computerized maintenance management system)? Accessed January 17, 2024, from https://www.ibm.com/mx-es/topics/what-is-a-cmms
3. Toyos, S. (2023, March 21). IoT and APM: the ideal combination for efficient asset management. Consulted on January 17, 2024, from https://www.fracttal.com/es/blog/iot-y-asset-performance-management#ayudarAPM
4. Sircar, A., Yadav, K., Rayavarapu, K., Bist, N., and Oza, H. (2021). Application of machine learning and artificial intelligence in oil and gas industry.
5. Velthuis, N. (2021). The Shell journey towards global predictive maintenance. Retrieved January 18, 2024, from https://www.shell.com/energy-and-innovation/digitalisation/news-room/_jcr_content/root/main/section/list/list_item_1405839260/text.multi.stream/1650525120832 /dabc9c17a2c9a00d39cb4f442e75d667920c8562/the-shell-journey-towards-global-predictive-maintenance-velthuis.pdf