- By Kin How Chong
- July 03, 2024
- InTech Magazine
- Feature
Summary
Analytics are revealing hidden plant insights that drive operational efficiency and profitability.
In the age of information, remote monitoring technologies offer countless benefits for manufacturers. Using data generated by sensors installed throughout industrial processes, engineers and operators glean valuable insights into real-time critical process parameters, equipment performance and environmental conditions, helping teams optimize plant operations and reduce expenditures. Additionally, remote monitoring enables early detection of potential safety hazards, prompting plant personnel to act swiftly and prevent upsets.
With effective monitoring and centralized control at remote operations centers, subject matter experts (SMEs)—collectively process engineers and data scientists—can proactively keep tabs on every operational unit throughout the enterprise, minimizing unplanned downtime and equipment failures. However, there are challenges to implementing remote monitoring effectively.
Smart process surveillance
Today’s manufacturers rely heavily on sensors and equipment that generate massive amounts of data. Complex petrochemical and refining operations, for example, require data collection and subsequent analysis from numerous geographically-dispersed sources, often in harsh environments, to ensure efficient and safe production.
Operational data is often housed in various locations—such as process historians, data lakes and other databases—varying by equipment type and manufacturer. As a result, it can be difficult to standardize and deploy a centralized remote monitoring solution. This creates delays in identifying and addressing critical issues, which can impact production and pose safety risks.
Moreover, dispersed operations often lack the necessary software tools to analyze time-series data effectively. This creates the common industrial paradigm of “data-rich, information-poor,” and despite significant investments in storage, the return on investment is minimal when data remains unused.
These issues are further compounded by the complexities of integrating many modern monitoring systems with existing legacy infrastructure, including:
- Challenges connecting the two systems, relying on outdated and unsupported communications protocols.
- The need to upgrade some legacy sensors for compatibility with the new monitoring software.
- High costs and time-consuming commissioning to align both systems.
Historically, extracting value from remote monitoring systems required specialized skillsets. In most cases, effectively deriving insights from data requires coordination between engineers—who understand the process operation—and data scientists, who are trained in coding. However, not all plant personnel possess the skillsets required to perform these tasks.
Unlock powerful insights
Advanced analytics platforms bridge the gap between skillset limitations and operational insights, providing extensive support for connecting to and extrapolating meaning from data spread among different locations, regardless of the format or structure. This is accomplished with alignment algorithms and protocols that ensure data consistency and accuracy.
By automating data alignment and alleviating manual efforts, these software platforms provide significant advantages for remote monitoring, which frees up valuable SME resources and reduces the potential for human error.
Modern advanced analytics platforms offer a range of powerful tools for data contextualization, calculation and asset scaling, facilitating extraction of valuable insights from consolidated data. These accessible platforms require no coding skills, empowering users to quickly become proficient in the software, even those with limited technical expertise.
Beyond ease of use, these platforms provide advanced features for complex analysis and calculations, including predictive analytics, machine learning and statistical modeling. Additionally, extensibility features allow users to operationalize custom calculations, empowering them to not only analyze historical data, but to also predict future outcomes and optimize processes accordingly.
Better monitoring across industries
In recent years, industrial organizations are increasingly leveraging advanced analytics platforms to remotely monitor their operations. This approach is providing positive benefits in many industries, improving efficiency, reducing costs and increasing profitability, as demonstrated in the following cases.
Improved furnace decoke performance. Decoking—the removal of coke deposits from the internal surfaces of furnaces and reactors—is a vital process for maintaining efficient and safe operations. Although it varies based on the furnace and on organizational practice, some of the most commonly monitored parameters include furnace temperature, furnace pressure, steam and gas flow rates, decoking duration, effluent composition, coke removal rates and coke quality.
Poor decoking has several negative consequences, such as reduced heat transfer efficiency, which decreases furnace capacity and production rates. Additionally, lower performing furnaces result in higher energy consumption, requiring more fuel to reach optimal temperature and maintain target production rates. Poor decoking also causes frequent maintenance shutdowns, resulting in unplanned downtime and production schedule disruptions.
One global oil and gas company deployed Seeq, an advanced analytics platform, to closely monitor its decoke procedures, reducing engineering time spent creating dashboards by 20% and improving furnace decoke performance by 10%. The solution enabled engineers to:
- Establish conditions for each furnace decoke parameter and assign scores based on a stringent performance matrix, using tools in the software.
- Calculate overall decoke quality by synthesizing all scores.
- Visualize performance using built-in tools, such as Histogram, which incorporates an adjustable display range for viewing specific time periods of interest (Figure 1).
Efficient distillation column operation. Differential pressure (DP) is an important parameter in distillation columns that provides valuable information about the column's state and efficiency. This term refers to the pressure difference between two points within the column, which is usually measured across the trays or packing.
When differential pressure climbs significantly above expected values, it is usually a sign of flooding, a critical situation that can arise in various processes where liquid holdup becomes excessive, hindering vapor flow and reducing separation efficiency. This can severely tarnish final product quality and overall production.
Monitoring DP closely can enable early detection and alerting prior to flooding, prompting corrective action to minimize damage when equipment malfunctions, feed compositions change, or blockages occur. It also helps reduce plant downtime and operational expenditures.
Setting up a DP monitoring dashboard is usually challenging because readings are highly prone to noise or fluctuations. As a result, developers must implement signal filtering to differentiate between meaningful changes and random variations. While a sudden increase in DP usually indicates flooding, there are other factors that can cause fluctuations, such as changes in feed composition or vapor flow. To distinguish between flooding and normal variations, additional data analysis and experience are required.
At a global petrochemical and refining company’s remote monitoring center, process engineers adopted a modern advanced analytics platform to monitor the performance of multiple distillation columns. As a critical data cleansing step, the engineers applied signal smoothing to remove random variation from noisy DP signals, excluding downtime data. The team closely monitored the cleansed DP signal along with the reflux flow rate of the distillation column in an XY plot (Figure 2).
To gain additional insight and compare the characteristics of the DP versus reflux profile over time, the engineers color-coded the plot based on fixed time period conditions. They also added a high limit to the plot to detect anomalies, such as abnormally high DP readings.
However, the task did not end here. The team scaled the same analysis to multiple distillation columns by creating asset trees and swapping the asset from one distillation column to another (Figure 3). This enabled scaling DP monitoring to over 100 columns, and it standardized the workflow across a large monitoring center with more than 200 engineers.
Optimized valve maintenance. Valves play a crucial role in many industrial applications by regulating the flow of fluid or gas through pipes and equipment. However, valve performance can be difficult to predict in real-time, making it challenging to maintain these assets effectively.
Maintenance is critical to keep valves operating optimally and to prevent unplanned downtime. On one hand, pre-scheduled preventive maintenance is costly and time-consuming because preexisting valve conditions are not considered. However, on the other hand, it reduces unexpected downtime, which has the potential to hamper production, reduce revenue and potentially damage ancillary equipment or harm the environment.
Obtaining the best of both worlds, an oil and gas company implemented an advanced analytics platform to conduct condition-based valve health analysis. The solution continuously monitors valve parameters—including apparent stiction, cycle duration, rate of travel and cycle count—to generate a health score and preemptively detect valve failures.
These key performance indicators (KPIs) are amalgamated and displayed using Treemaps, which show overall valve health at a glance so maintenance teams can easily prioritize their efforts (Figure 4).
Subsequent dashboards show detailed trends of all valve health KPIs, helping identify patterns and trends impacting valve performance. This also helps identify when corrective actions are required, and it ensures limited maintenance resources are utilized effectively.
One leading agriculture company used this same approach to reduce fugitive emissions by monitoring nitrogen blanket control valves, saving an estimated $120k per year in wasted nitrogen per faulty valve.
A future of smart remote monitoring
In today's connected landscape, remote monitoring is increasingly becoming a cornerstone of manufacturing, allowing SMEs to collaborate and innovate from anywhere in the world. However, implementing effective monitoring is not without its challenges.
Advanced analytics platforms accelerate the time to value, automating data aggregation from multiple locations, as well as providing operation-wide context and optimization insights. These solutions are improving process safety and efficiency, empowering manufacturers to increase uptime, produce more product and maximize profitability to remain competitive in continuously-evolving markets.
All figures courtesy of Seeq
This feature originally appeared in the June 2024 issue of InTech digital magazine.
About The Author
Kin How Chong is a Senior Analytics Engineer at Seeq. He has an engineering background with a BS in chemical engineering from Universiti Kebangsaan Malaysia and an MS in data science from the University of Malaya. Kin How has more than a decade of experience working for and with chemical manufacturing companies to solve high-value business problems. In his current tole, Kin How enjoys supporting industrial organizations as they maximize value from their time series data.
Did you enjoy this great article?
Check out our free e-newsletters to read more great articles..
Subscribe