PTQ Q2 2023 Issue

• Resource availability – both business and IT : The busi- ness must decide what information it needs (the KPIs). Both parties need to be available within a given timeframe to design the solution to ensure it works with the business processes to optimise decision-making. • Time and money: Defining and building such solutions can be time-consuming and, therefore, costly. This is par- ticularly true with ‘one-of-a-kind’ dashboards such as those for specialised processes or smaller organisations. While a multinational oil company could build a dashboard for a fluid catalytic cracker (FCC) operation that could be reused across several refineries, a single refinery organisation can- not benefit from such economies of scale. • Time to complete : Even if the organisation can afford to build bespoke dashboards, the elapsed time from project conception to completion may be significant. In KBC’s experience, a typical unit bespoke project using a commonly deployed real-time data and analytics plat- form will last around 6-12 weeks, allowing time for stake- holders to agree and define the solution as well as build and test it. • Maintaining solutions : Business objectives change, and software platforms evolve and should have the latest secu- rity updates. It is a false economy to forget maintenance when selecting a dashboarding solution. To conclude, any solution developed must align with busi- ness processes and address current challenges facing the business (maximise work efficiency, transfer knowledge, and identify opportunities) while being fit for purpose, scal- able, and extendable. Case study KBC has been exploring whether ‘out-of-the-box’ dash- board solutions can address the challenges of building effective dashboards rather than individually tailored solu- tions. These ‘kits’ also capture process-specific analysis to enhance the decision-making process. Below are some advantages of these kits compared to a customised solution. Faster and lower investment route to value Across the refining industry, units of the same kind at dif- ferent sites are reasonably similar. With access to the right expertise, it is possible to draw a list of common KPIs for, for example, an FCC and build a set of visualisation tem- plates to display this information in a compelling and logical manner to enhance decision-making. KBC has built a ‘kit’ structure that supports contextual- ising and analysing data. The solution was developed to enable easy customisation for different units (of the same kind) across the industry. The kit can easily be configured to display the correct number and name of feed and product streams and the differences in the unit configuration, such as whether the FCC has one or two risers and/or regenera- tors. The kit is designed to be installed on the client’s exist- ing data/analytics platform. Compared to a bespoke solution, such a kit solution can be delivered faster and at a lower up-front cost. The time savings, leading to early value identification, can make the

and artificial intelligence/machine learning in a subsequent update). Furthermore, the solution can be improved as the rollout progresses. These solutions need three common elements: • Reliable, integrated data sources and storage systems (starting with an on-premise plant historian, extending to data lakes and cloud-based storage). • Analytics aligned with the company’s management needs. • Insights gleaned from the data disseminated to the actors and decision-makers. The following discussion assumes that data have been logged and stored efficiently (whether on-premises and/or in the cloud) and are easily accessible. Data silos still exist to a greater or lesser extent in most organisations for histori- cal operational and/or technical reasons. Siloed data can be a major barrier to efficient decision-making. When decision- makers lack access to all the relevant information, or if access is delayed, such as by manual steps to synthesise data, deci- sions will be suboptimal and/or late. Both situations result in lost opportunities. In terms of analytics, the first step starts with under- standing what should be monitored, analysed, and why. In a typical process unit, this means identifying KPIs and their relative importance. A seemingly limitless supply of data and the computational power to process it are no replacement for engineering and scientific expertise. At the least, data quality should be checked. Poor data offer little value, and inconse- quential correlations and relationships in the data should not cause distractions. Engineering skill is also needed to ensure that the scope and complexity of the analytics match the size and nature of the problems. Data analysis and process monitoring only yield value if they lead to action. Real-time optimisation and automated optimisation solutions minimise the need for human inter- vention in plant optimisation but are often the most expen- sive option and unsuitable for many processes. Also, it may be more appropriate (financially and technically) to start with a less complex solution to develop over time. So, to enhance the decision-making process, what are the best ways to present information when considering an advisory solution? The use of dashboards has become ubiquitous across industries and extends into the consumer’s personal life through mobile device apps to monitor bank balances, fit- ness, and domestic energy use. Dashboards, a powerful industry tool where user-persona dashboards can be linked to a ‘single source of truth’ data source, can be customised to specific consumers and enable all decision-makers to access the same core data. When displayed, it enhances individual decision-making functions. The right combination of impactful graphics backed by figures and notifications allows the consumer to absorb key information quickly to drive decision-making. Conversely, a poorly designed dashboard, loaded with too much informa- tion and indiscriminate notifications, is, at best, annoying and, at worst, will be ignored. Challenges of building effective dashboards If dashboards are the future, what are the challenges of designing and building them for maximum impact?

PTQ Q2 2023