Bridging the Knowledge Gap with AI

Summary

As experienced operators and professionals retire, process manufacturers are facing a significant knowledge and skills gap for incoming workers. Artificial intelligence (AI) can help manufacturers capture and retain valuable historical knowledge and ease the transition for younger workers. Bayer Crop Science found one solution to help capture knowledge from their experienced workers through an AI-powered Smart Search system for their plant process management (PPM) software.

How AI enables efficient knowledge transfer

“Knowledge transfer is a big issue in shift operations,” said Matthias Hesskamp, the head of Site Operations and Excellence at Bayer Muttenz. “Shifts are producing and generating data 24/7. Day Operations, responsible for problem-solving, only works 40 hours per week. They face the challenge of processing data that is generated constantly every day.”
 
Process industries typically operate 24/7, with three or more shifts across the day and numerous different teams and areas of responsibility, including engineering, production, R&D/technical, maintenance and management. Bayer implemented an enterprise platform that improves communication and information transfer across shifts and teams. The software acts as a centralized PPM solution, gathering both user-derived data (such as shift notes, maintenance logs and inspection observations) and automated data from sensor and equipment readings.
 
All these inputs generate vast volumes of information every single shift. Mining this data can help employees discover opportunities for continuous improvement, identify best practices, learn from prior mistakes and find solutions for recurring problems. But sifting through mountains of data to find the information needed can be time-consuming and cumbersome for human workers. Often, valuable knowledge and insights remain hidden within PPM software.
 
That’s where AI comes in. Tools like machine learning (ML) allow AI to quickly sort through large volumes of data to identify patterns and surface insights that would be difficult or impossible for humans to discern within a reasonable timeframe. National Language Processing (NPL), another AI tool, enables the system to understand queries and instructions provided in plain human language, derive meaningful information from text-based sources, and return results that humans can understand.
 
eschbach worked with the Bayer Crop Science Muttenz site to develop a customized Smart Search system for their shift handover software. Using NPL and ML, the system can now understand the meaning and context of a query and surface the most relevant results. This is very different from a simple keyword search, which may return hundreds of non-meaningful results or fail to find the right information because the exact keyword was used, or data entries are incomplete or mislabeled.
 
The Smart Search system was trained on industry- and plant-specific terminology and data formats and informed by user groups, employee workshops and onsite investigations that shaped development of the final product. The result is a search system that is highly customized for Bayer’s workflows, language, and user requirements.
 
Using Smart Search, employees can now quickly uncover the information they need to perform their jobs effectively. For example, if a problem develops at a particular point in a process, they can simply submit a query (e.g., “Why is Product A brown instead of clear?”) and quickly discover any previous instances of the problem and what was done to resolve it. The Smart Search system has reduced the amount of time employees spend searching for relevant information, often from several hours to mere minutes. This enables faster troubleshooting and problem resolution and greater worker efficiency.

A next-generation knowledge management platform

Smart Search has transformed Bayer’s PPM software from an information repository and shift communication system to a centralized knowledge management platform. Workers can quickly sort through years or decades of information to find what they need at any moment. This means that the wisdom and lessons of the past are stored and readily available for today’s workers.
 
Knowledge management and transfer will be essential to help process manufacturers adapt to new workforce realities. In the U.S., nearly one-fourth of manufacturing workers are age 55 or older, and The Manufacturing Institute projects that nearly 2.1 million manufacturing jobs could go unfilled by 2030 due to skill gaps in younger generations. Similar skills shortages are projected for Europe and other parts of the world. As the baby boomer retirement wave continues and fewer Gen Z workers choose manufacturing as a career path, talent acquisition, development and retention will be critical issues.
 
A knowledge management platform with AI can help companies retain knowledge from experienced operators, technicians and engineers and make it accessible for the next generation. This includes valuable tacit knowledge: the “on-the-job” knowledge gained through experience and observation that exists outside of formal training programs and SOPs. For example, an experienced process engineer may know that a formulation has to be tweaked at certain times of year to account for environmental conditions, or a long-time maintenance director may know just what to do to resolve an idiosyncratic issue for a piece of machinery. These are the types of knowledge that are often lost as older workers leave the workforce—but may be hiding within maintenance logs, shift notes and other human-generated records. A knowledge management platform with AI tools brings this kind of tacit knowledge to the surface, acting almost like an experienced mentor for newer workers.
 
As Gen Z enters the workforce, AI knowledge management tools will help them get up to speed quickly and maximize their on-the-job productivity. Younger workers appreciate cutting-edge technology tools that can help them do their jobs better. Maximizing the effectiveness of the incoming workforce will help companies address the skill gap and get more done with a smaller workforce. By harnessing the power of AI to amplify human potential, process manufacturers will be better positioned to meet the challenges of tomorrow.