ROI and measurement in chemicals
Chemicals plants use AsscherAi to measure ROI by analysing production line data, identifying yield drift and feedstock variability, and comparing leading measures before and after catalyst introduction, enabling informed decisions on rollout and optimising production processes.
A production manager at a chemicals plant must decide this week whether to roll out a new catalyst to all production lines, and the decision will be based on the return on investment (ROI) of a trial run on one line, but the complexity of continuous chemical processes makes it difficult to isolate the effect of the catalyst.
Chemicals industry challenges
The chemicals industry presents unique challenges when measuring the ROI of an intervention, such as the introduction of a new catalyst. Yield drift, where the output of a process changes over time due to factors like equipment wear and tear, can mask the effect of the intervention. Feedstock variability, where the quality of the input materials varies, can also impact the outcome. Additionally, plant-to-plant recipe differences can make it difficult to compare results across different production lines.
These factors can lead to a situation where the counterfactual, or what would have happened without the intervention, is invisible, making it challenging to determine the true impact of the catalyst. This is particularly problematic in continuous processes, where small changes can have significant effects, and tight yield and safety envelopes leave little room for error.
Leading measures
Despite these challenges, there are leading measures that can be observed to gauge the effectiveness of the intervention. A shift supervisor can check the maintenance log to see if there have been any changes in equipment performance or downtime. The category manager can compare the cost of raw materials and energy consumption before and after the introduction of the catalyst. These measures can provide early indications of whether the intervention is having the desired effect.
By monitoring these leading measures, the production manager can get a sense of whether the catalyst is having a positive impact, even if the overall ROI is difficult to determine. This can help inform decisions about whether to roll out the catalyst to other production lines.
Aggregate outcome metrics
Aggregate outcome metrics, such as overall plant productivity or profitability, can move for unrelated reasons, making it difficult to determine the impact of the intervention. For example, changes in market demand or fluctuations in raw material prices can impact these metrics, even if the catalyst is having a positive effect. This is why it is essential to focus on leading measures that are more directly related to the intervention.
Most people get wrong the idea that aggregate outcome metrics are a reliable way to measure the ROI of an intervention in the chemicals industry. They are wrong because these metrics are influenced by too many factors, making it impossible to isolate the effect of the intervention. A more nuanced approach is required, one that takes into account the complexities of the process and the various factors that can impact the outcome.
Baselining before rollout
Baselining the process before rolling out the intervention is crucial to determining its effectiveness. This involves collecting data on the leading measures and aggregate outcome metrics before the intervention, to create a benchmark against which the results can be compared. By doing so, the production manager can reconstruct the counterfactual and determine the true impact of the catalyst.
Reconstructing the baseline after the rollout is not a viable option, as it would require making assumptions about what would have happened without the intervention. This can lead to inaccurate conclusions and poor decision-making. By baselining before rollout, the production manager can ensure that the evaluation of the intervention is based on robust data and a clear understanding of the process.
For more information on how to baseline your process and measure the ROI of an intervention, visit our website or contact us directly through our contact page.
Limitations
This approach to measuring ROI in the chemicals industry is not a panacea, and there are situations where it may not be applicable. For example, in situations where the intervention is very small or the process is highly variable, it may be difficult to determine the impact of the intervention. In these cases, alternative approaches, such as simulation modeling or statistical process control, may be more suitable.
In some cases, the use of AI and machine learning algorithms can help to identify patterns and correlations in the data that may not be apparent through traditional analysis. However, these tools are not a replacement for careful planning and baselining, and should be used in conjunction with a thorough understanding of the process and the intervention.
Frequently asked questions
How can AI help measure ROI in chemicals production?
AI helps analyse production line data to identify key factors affecting ROI, such as yield drift and feedstock variability.
What are leading measures in chemicals production?
Leading measures include equipment performance, downtime, and raw material costs, which can indicate the effectiveness of a catalyst introduction.
Why are aggregate outcome metrics insufficient for ROI measurement?
Aggregate metrics can be influenced by unrelated factors, making it difficult to isolate the impact of a catalyst introduction, and requiring a more nuanced approach.
How can baselining help in ROI measurement?
Baselining involves collecting data before a catalyst introduction, creating a benchmark to compare results and reconstruct the counterfactual, ensuring a robust evaluation of the intervention.