Case Study: Data Management

AI Recipe Optimization Enhances Paint Line Performance

A growing manufacturer partnered with Mutually Human to overcome data challenges from rapid acquisitions. By implementing a centralized data lake and real-time BI dashboards, the company streamlined operations, improved inventory management, and enhanced decision-making. The solution also reduced system integration times and laid the groundwork for future scalability and advanced analytics.

Business Challenge:

Manual machine settings led to costly waste and inconsistent production quality for this automotive manufacturer.

A Tier 2 automotive manufacturer was experiencing persistent inefficiencies on its paint line due to a trial-and-error approach to machine settings. Operators were responsible for adjusting four critical settings while accounting for over 25 unpredictable variables—including job size, humidity, and paint hardness. As a result, production outcomes were inconsistent, leading to excessive scrap, material waste, and frequent delays.

Additionally, issues with incorrect settings often weren’t discovered until after a job was completed, making it difficult to correct errors in real time. Because of these limitations, the company needed a smarter solution to reduce waste, automate decision-making, and ensure consistent quality throughout production.

Approach:

Mutually Human developed a custom AI model to optimize paint line settings in real time.

To address these challenges, Mutually Human partnered with the manufacturer to build an AI-powered recipe optimization solution. This involved creating a machine learning model capable of writing directly to the programmable logic controller (PLC), allowing the system to automatically adjust settings based on live data.

Rather than rely on every available data field, we focused on optimizing the inputs. From 40 possible data points, we selected 25 key variables that had the greatest influence on outcomes. We also trained the model using quality metrics—such as hardness, sheen, and blemishes—to ensure it could balance material use with finished product standards.

To ease the transition, the implementation was rolled out in two phases. First, operators used an app to review and validate the model’s recommended settings. Then, the system was fully automated, giving the model control over real-time adjustments for maximum efficiency.

Results:

The recipe optimization solution delivered measurable improvements across the board—saving time, reducing material waste, and improving output quality.

Optimized Machine Run Times

Real-time adjustments kept production flowing smoothly and reduced delays.

Lower Scrap & Energy Use

Improved settings led to fewer errors, less material waste, and reduced energy consumption.

Consistent Paint Quality

Automated controls produced reliable results in hardness, sheen, and surface finish.

Improved OEE Performance

With fewer manual interventions, the line achieved better overall equipment effectiveness.

Greater Operator Confidence

Automation reduced stress, increased trust in the system, and allowed teams to focus on higher-value work.

Great projects start with a great conversation.

Let’s talk about your unique challenges and explore how we can craft a solution that fits your needs. Whether you’re looking to streamline processes, innovate with new technology, or bring a bold idea to life, our team is here to help. Reach out today and take the first step toward turning your vision into reality with a trusted partner by your side.