Chemical companies are looking for new ways to thrive amid an evolving and increasingly competitive marketplace. Industrial firms were heavily affected by the pandemic and had to enable remote working and transform operations simultaneously. They needed to increase agility and resilience to respond to dynamically changing market demands.
The additional pressures of compliance, reducing costs, rising competition, and growing demand for sustainable chemical products are all fueling an industry-wide drive for improved reliability, efficiency, and safety.
Solving these challenges requires a continuous focus on optimization to reach operational and maintenance excellence. As such, chemical companies are looking to accelerate digital transformation and use performance intelligence to improve critical asset performance and promote connected workforces.
Zero downtime, maximum performance
By harnessing data and models to build an advanced asset performance management solution – including artificial intelligence (AI) and machine learning (ML) – firms can monitor critical assets and predict failure towards a goal of zero plant shutdowns.
Forward-looking companies are looking to end-to-end Digital Reliability Platforms (DRP) to predict equipment health, monitor performance, and enable advanced maintenance to eliminate unplanned downtime. A case in point is Thai petrochemicals firm SCG Chemicals – which coined the term DRP and pursued a digital transformation initiative with AVEVA to harness and leverage data for operational benefit.
Using a mix of on-premise and cloud-based applications, the DRP solution integrates online and offline equipment and process data to visualize plant performance, enhance workforce efficiency, and apply AI for predictive maintenance and resolution.
Digital Reliability Platform: 4 Ingredients
DRP utilizes digital innovations to increase maintenance efficiency. The central components of DRP include: Predictive Analytics; Data Center; 3D Virtual Plant; and Mobile Operator.
Predictive Analytics – Predictive analytics infuses AI into the solution enabling operations and maintenance personnel to be more proactive on the job. Instead of shutting down a section of the plant immediately, a problematic situation can be assessed for more optimized outcomes. Assets that are not performing optimally can be evaluated before they fail, or necessary maintenance can be scheduled during planned downtime or when is most convenient.
Predictive software tools enable optimized maintenance schedules, ensuring the best resources – such as qualified personnel or replacement parts – will be available to minimize disruptions to operations. When detecting an early-stage problem, the software leverages deep learning to determine the remaining useful life forecast of the asset.
The power of predictive analytics lies in its ability to transform raw data into easy-to-understand, actionable insights that result in improved reliability and decision-making through an intuitive no code implementation process.
Data center – The DRP gathers offline and online data into a centralized data management platform which serves as an operational data repository and a base for policy management rules configuration. The data center collects real-time data, time series sensor data, contextualizes, and feeds it into the predictive analytics model.
3D Virtual Plant – A virtual three-dimensional plant – which has complete machine and behavior information represented within the model – allows management to plan work efficiently, mitigate risks and respond to emergency events quickly if they arise.
A Virtual Plant solution can provide an immersive and touch-based visualization solution that enables inter-discipline collaboration and fast information through a range of hierarchical dashboards for equipment status, alarms, and health status.
Mobile Operator – Mobile operator software deployed on mobile devices, such as tablets, enables disconnected data to be collected and integrated to the data center for analytics and analysis. Defined work tasks and workflows enable actions to be consistently executed. This ensures that operator rounds, maintenance checks and safety and environmental inspections are properly completed using best practices and provides a platform approach to continuous improvement.
Boosting Reliability and Cost Savings
With its tightly integrated business, key Asian industry player SCG Chemicals was at risk that individual equipment failure could shut down the entire production chain with direct implications for top and bottom-line financial performance.
To address this risk, SCG Chemicals and AVEVA implemented a DRP to enable a central hub for data collection, analysis, visualization, and maintenance operations enabling the connected worker to make fast, informed and optimized decisions that improve efficiency, safety and profitability.
With a range of dashboards from the business unit level down to individual equipment, the DRC changes how SCG teams interact with their data by providing a single interface to all asset information.
Once the DRP was installed, plant reliability increased from 98% to near 100% and a significant cost saving was delivered. Maintenance costs decreased too – delivering savings of 40% through greater operational and workforce efficiency, as well as improved work scheduling.
The chemical industry has been notoriously slow to change given its pervasive safety and regulatory requirements, but as global industry transforms, some skills will fade as others become necessary.
The core tenets of Industry 4.0 include the interconnectivity of people, processes, technology and the need for real-time insight at the levels closest to the action. These values are not new and extend from the operational excellence efforts empowering our teams today.
As the chemicals industry continuously improves, digital transformation is not a technological destination but the next step in process and business evolution.
Author: Sean Gregerson, Vice President - Global Asset Performance Management, AVEVA
Disclaimer: The opinions expressed within this article are the personal opinions of the author. The facts and opinions appearing in the article do not reflect the views of ICN and ICN does not assume any responsibility or liability for the same.