Specialty Chemical Production: Advantages of Batch Analytics

Summary

The chemical industry is currently going through turbulent times due to COVID-19. Market demand has shifted greatly and production levels may have been impacted negatively or in some cases even positively. In many cases, we see a rise of batch production due to more individual customer demands. Facing these turmoil times and to even come out on top of the market requires creative contribution from all employees at all levels of the organization. Data can support creative ideas or even initiate new ideas for improving operational performance in the new situation. This includes operations, where a wealth of data is available for years.
 
The goal of batch manufacturing is to safely produce a maximum yield batch within product quality specifications in the shortest amount of time and with a minimum amount of waste. Achieving that goal comes with many challenges, particularly as the environment gets more competitive. Operators are working in highly- complex and dynamic areas where large amounts of data must be managed and integrated in order to generate positive outcomes and eliminate opportunities for undesirable processing events or end-of-batch quality issues. 



Forward-thinking manufacturers are embracing self-service batch analytics to create digital work environments that offer benefits that are usually immediate and substantial. This approach has been shown to strengthen manufacturers’ market positions resulting in more profitable factories, which also puts them ahead of the curve in technology-enabled production. In fact, between 2019 through 2024, Research and Markets predicts that 'enabling technology' such as batch analytics, machine condition monitoring, artificial intelligence, and machine learning are anticipated to become the fastest-growing and most-valued segment of the IIoT in the chemical industry. Modern, agile, cloud-based batch analytics that provide end user self-service have helped to increase adoption rates by chemical manufacturers and have proven to provide substantial value to chemical industry adopters. 
 

A compelling case for investing in data analytics

Growth in analytics adoption is supported by the positive influence operating profitability and return on investment capital (ROIC) have on a company’s value and market standing. The ROIC performance of specialty chemicals is increasing and even outperforming the diversified and commodities segments. This surge in specialty chemical performance coincides with the growth of Total Return to Shareholders (TRS), which indicates that an investment in a specialty chemical portfolio is clearly tied to stronger operating profitability.
 
This obviously provides a clear incentive for chemical companies to improve operating profitability. In general, there are some similar financial aspects within both commodity chemical and specialty chemical companies’ control, such as cost position, working capital, mergers and acquisitions as well as  operational excellence. Driven by unique product innovation, as well as favorable end market choices, specialty chemical companies possess a bigger influence over market prices when compared to companies from the commodity sector, where the market price is heavily influenced by external factors.
 
This influence indicates significant potential for specialty chemical companies. Operational flexibility combined with high market and price control often leads to improvement in ROIC performance and may even help performance sustainability

Industry 4.0 and a digital workforce go hand in hand

With the advent of Industry 4.0, data analytics solutions have evolved to play a key role in improving operational efficiencies. Regardless of the industry segment, the potential is estimated to be in the range of 3-5% improvement in return on sales.
 
A push for Advanced Process Control (APC) was a focus in the 80’s and 90’s as the main part of a sustainable solution to improve operating efficiency. However, the spread of APC solutions has been inhibited by critical shortcomings such as when encountering a highly variable and uncertain environment. 
 
Two solutions have evolved to mitigate the shortcomings of APC. These are:

• Utilizing generic data science to solve operating problems without the necessity for a data scientist intervention

• Self-service analytics, which empowers the process expert with advanced analytics tools that can directly solve the bulk of day-to-day operating issues

Self-service analytics brings a myriad of opportunities across the organization and - along with a low cost of implementation when compared to classical APC solutions - has significant potential to empower operational personnel to creatively contribute to face current volatile market circumstances.  It is estimated that up to 10,000 small and mid-size manufacturers can increase their performance opportunities and help gain profits of up to more than $500 million with a self-service analytics approach. This can be compared with potential gains of about $50 million with general data science solutions (source: McKinsey research).
 
Generally, both self-service analytics and APC have improvement potential and ideally should work in sync to build a mature digital environment.   
 

Reaping the benefits of self-service solutions

The benefits of process data analytics and self-service solutions can lead to increased operating efficiency and a stronger market position. Within specialty chemicals, a digitally enabled workforce using self-service batch analytics solutions can efficiently increase throughput and quality through solving daily analytics challenges themselves, without the need for a data scientist intervention. These solutions include:

• Eliminating waste on high value batches

• Reducing long cycle times in order to more quickly meet customers’ demands

• Enabling an increase in flexibility and a more customized production utilizing smaller batch sizes.

Based on experience, a self-service solution in the context of batch analytics plays a big role in solving those issues without the use of a data scientist.
 
In order to fully gain all the benefits hidden in process data, such a data analytics solution must be robust and easy to use and has to offer one common platform to analyze data from continuous process steps downstream as well as from batch operations upstream. In this way, the process eliminates a collection of island solutions for specific process problems across the value chain of analyze, monitor, and predict, which could hinder the value potential hidden in the data.