Plant floor data can get messy and overwhelming for food manufacturers. In today’s plant, instrumentation and sensor information can generate gigabytes of data every second. Industry 4.0 is still young, so food manufacturers are still figuring out how to combine data upgrades with continuous improvement (CI) programs. More plant floor data can be cumbersome, so how do manufacturers keep moving forward?

A recent webinar produced by CESMII, titled “Smart Manufacturing Mindset – Think Differently: Continuous Improvement,” offered real-world insights into this issue from Lisa Zasada, director of reliability and improvement at General Mills, Patrick Gaughan, partner at Axiom Manufacturing Systems, and James Ricci, managing director at AMBE Engineering, LLC. (*The transcript of this discussion has been lightly edited for clarity and brevity purposes)

This smart manufacturing webinar kicked off with the question on how manufacturers should incorporate plant data upgrades.

“General Mills has focused on top opportunities for the business and is looking for more data insights with its global footprint. But food manufacturing is a people business and leading change management is foundational,” says Zasada. “It doesn't matter whether you're doing continuous improvement or a smart manufacturing initiative. Companies need to leverage their growth mindset. Companies need to lean in and build new capabilities to use data in different ways and encourage experimentation.”

General Mills has a long history with continuous improvement. Jim Wetzel, the previous director of engineering and reliability at General Mills, led corporate-wide initiatives focused on exception-based reporting. During his tenure, the company focused on determining centerlines or recipes for key parameters of a system/unit of operation, a core element to a continuous improvement program. Tracking deviations from centerlines can become a basic or starting methodology to exception-based reporting.

For the last five years, food manufacturers have focused on automating repetitive tasks to free up operators to do other activities. One of those activities is tracking deviations to improve throughput. In 2022, FOOD ENGINEERING’s State of Manufacturing Report revealed that food and beverage leaders are happy that demand is increasing but efficiency continues to lag. The report stated, “61% of food and beverage leaders said they want to expand their flexibility on the production line, and 55% want to expand their packaging lines and production facilities.”

AMBE Engineering’s Ricci emphasized actionable data for continuous improvement programs during the discussion. “There are many times where teams want to go with a traditional lean fishbone diagram, but you don't have great data to help guide the team,” he says. “So organizations rely on tribal knowledge.”

To avoid this, Ricci stresses capturing data on a specific machine and isolating this machine. “This would be maintenance information and all that data being pulled through the system, which allows you to get much more targeted,” says Ricci. “The chances of success in a rapid improvement—or experiment—and not just success but sustainability just goes through the roof.”

AMBE Engineering offers optimization, supplier recovery and crisis management services for manufacturers. While pilot projects are plentiful in manufacturing, solving production issues are cut and dry for many plant managers. Ricci cites that there's no need for elaborate return-on-investment (ROI) plants, as he believes discrete data solutions can be quite effective.

"Bringing it back to smart manufacturing, there’s a real opportunity to try new things and implement solutions because you're in an environment where AMBE wouldn't be there,” says Ricci. “Our team wouldn't be there unless things have really broken down.”

Ricci cited a client with production issues and how AMBE’s third-party perspective allowed the company to identify throughput issues with a specific machine. AMBE implemented an independent data analytical solution separate from the company’s industrial networking system. “The company says this is good information and it only took you 72 hours to start pulling really good data down,” says Ricci.

“In a crisis, our solutions are expensive assets. However, there isn't an ROI and this isn't a long-winded proof of value to management,” says Ricci. “It's important that technology (solutions) gets proven and companies can accelerate change. It's definitely a different take on how to implement a smart manufacturing mindset.”

Axiom Manufacturing Systems’ Gaughan believes simple technology solutions can provide enough data for rapid improvement projects that act as CI. “In today’s world, you take a video and load it to the cloud, and artificial intelligence (AI) parses that thing out, aligns all the data, gives you all the analytics on that data.”

Experimentation versus Pilot Projects

General Mills is a global food company, and business alignment is crucial. “The language of data, technology, continuous improvement and manufacturing doesn’t always align,” says Zasada. “Sometimes you can end up in conversations where it’s really difficult to decipher what is being said by different players. This is where the role of growth mindset and learning agility is critical.”

Zasada cited small experiments—an agility mindset—at General Mills to be essential and provide a definition. “I view experiments as being much smaller than a pilot project, and experimentation is a new way of operating, solving a problem or (implementing) a new technology,” says Zasada. “But I think this notion of pilot purgatory is something we're all aware of and have experienced.”

“I try to avoid the word pilot and move further to proof of technology and of value as very clear terminology because it points to an endpoint by which we're going to make a decision as an organization,” Zasada adds. “Understanding what you're trying to drive towards to add business value allows flexibility if a proof of technology or value doesn't go the way you expected.”

Validation is at the heart of this CI, but so is having business alignment and a smart manufacturing roadmap, according to Zasada.

The panel agreed that small CI or smart manufacturing steps could include adding cameras, which provide different fields of view in a production line and allow for contextualization. Ricci also added that a recent customer leveraged its security camera footage to isolate specific equipment for troubleshooting.

General Mills uses statistical or data analysis techniques for more complex issues. “We're doing some really exciting work right now with data on our manufacturing floor and contextualizing using models,” says Zasada. “And absolutely there is a strong component here of data analytics and statistical analysis.

Zasada points out, “having that expertise and bringing it to bear on some of the more complex problems is a cool part of the journey. It's unlocking some of these higher order problems that we have talked about and know intuitively are there, but have struggled to put the science behind it.”

A Leadership Culture and People 

While the panel discussion focused on data tools, measurement and troubleshooting, companies need leaders to emerge. “Technology changes exponentially, but people change logarithmically,” says Ricci. “Consequently, when processes keep changing, and you wonder why you can't sustain (technology adoption), it’s because the rate of change is greater than what the people are able to or willing to take on at the time.”

Ricci adds that companies and leaders need to recognize this fact. “At the end of the day, people must execute, understand and react to the data,” says Ricci. “Why bother spending money on technology if you're not going to change anything? So my thing is you got to keep people.”

Zasada echoes this point. “It's important that we don't lose sight of people and process. This is where we have to build capability,” says Zasada. “It's where we need to lead change management, and where we fall short on that the improvements won't be sustainable or they won't be embraced within a manufacturing environment.”