content provided by pleora

In part one of this article, we covered some of the advantages of AI for visual inspection and discussed how an electronics assembly company is using the technology to help human inspectors and track products. In part 2, well look at how a distillery uses the system for packaging inspection.  

AI and Brand Management

AI and decision-support can also help manufacturers ensure consistency and reliability for in-process applications. Dairy Distillery uses AI decision-support tools for their labeling and final quality control inspection processes to ensure consistent branding for their products.

The distillery is a small operation, producing about 1,000 bottles per day while competing against global players with massive marketing budgets. Key for the distillery is its unique shaped bottle, fashioned after a traditional milk bottle to reflect the company’s unique product manufactured from a dairy byproduct, and eye-catching labeling.

The bottle has three independent brand elements. The main label and cap sticker are both placed by a machine. A round, transparent emblem is then placed by a human, who must align the sticker with branding on the other two labels. The manufacturers had been using a machine for this process, but was consistently seeing a 50 percent failure rate. While the manufacturer has automated other steps in their process, it was easier and more economical to revert back to a manual process for emblem placement.

Additionally, as a manufacturer of luxury goods, there is a certain appeal to seeing how the human touch is part of the product. Part of the charm of visiting a distillery, sampling the products and maybe making a purchase, it talking with the people who put their time, passion, and expertise into each bottle. It’s not quite the same experience watching a robot produce and package a product.  

The challenge is, over a long shift, the placement of the emblem could drift from bottle to bottle. During the packing phase, an employee would notice the error and production would be halted as employees manually inspected bottles and manually removed and replaced the emblem.  

The bigger threat for the business; poorly labeled products would reach the store shelf, where they would reflect poorly on the brand. As a new product on the shelf, a consumer may question product quality based on a poorly labelled bottle. Potentially, the retail buyer could also reject the product, resulting in shipping costs and possible waste.  Adding to the challenge, the distillery produces multiple products with different labels, and as they expand in to global markets faces different packaging requirements for geographies. It’s easy for an operator to make a mistake.

To help make the human operator consistent, the distillery is using a customized visual inspection app. The operator places the bottle under the camera, with the app then identifying the brand elements on the machine-placed labels. On the display screen, the operator sees the real-time image of the bottle along with a virtual grid that guides the placement of the emblem. The app can be easy trained for the different brand elements depending on the product, and is especially helpful for new operators and seasonal staff as the learn brand elements for the different product lines.  

The visual inspection apps ensures consistency and accuracy for their valued brand. It saves them time and money if labels have to be removed and reapplied. They can confidently ship products knowing they will properly represent the brand on the store shelves. The system is easy to train, and the quality manager or operator can update the app for different products or changing requirements using a single good image. Over time, the AI model can also learn the brand requirements for the different packaging elements to automatically alert the operator on issues, including label defects.  

As the distillery has trialed the app, they have provided key feedback on other areas of their manual processes where automated decision-support could be beneficial to their operations. An inspection “pass/fail” app is in development that quickly lets operators see if labels are aligned. Down the road, the app could be trained for additional inspection on fill levels, cap seal, bar code readability, and more. The manufacturer can also use the app to gather data on errors to help pinpoint process issues. These are all areas where, if there is an issue, the product will be rejected by the store buyer. That leads to additional costs that cut in to profitability, including replacing the product, shipping, and waste. In addition, adding decision-support helps reduce stress for employees who are worried about a faulty product leaving the facility.

Making Subjective Decisions Consistent

One of the challenges with rules-based machine vision inspection is subjective decisions, especially where it may be a fine line between “good and bad”. Products with irregular grains and patterns, for example, are difficult to assess with machine vision. For example, automated inspection may have trouble distinguishing between a scratch on a piece of hardwood floor (“bad”) and the naturally occurring grain, knots and patterning desirable in high-end flooring products (“good”).

Inline inspection with AI is one way manufacturers are adding more subjective assessment to automated inspection. This is also an area where many manufacturers will rely on a human inspector to make a grading assessment. One challenge often raised by manufacturers is “how can I ensure consistency between my operators?” This is especially a concern in today’s tightening labor market, where a manufacturer may not be able to attract and retain highly skilled inspectors, or employee turnover means they are consistently training new staff.

With an AI-based decision support tool, the AI model can be trained to match the capabilities of a manufacturer’s best inspectors. Once the quality manager is satisfied with the AI model’s decision support, they can stop training the model and share the app with other inspectors. In essence, AI replicates the decision making capabilities, experience, and expertise of their best inspector and shared it across the production facility.

There is a great deal of complexity around AI, with lots of daunting terms. That usually leads to misconceptions about costs and deployment complexity. With AI decision-support tools, training and deployment can be simplified so any manufacturer can leverage the skills and expertise of their best inspectors across multiple production runs, facilities, or even with newly hired operators. As a result, manufacturers can start using more advanced technologies to help ensure higher quality, lower costs, and ultimately increased profitability.