Optimizing production processes and costs in manufacturing by using Deeploy
Fabric manufacturers all over the world face the same fundamental challenge – how to produce as many products with as little as possible resources. In that regard, Vlisco, a Dutch manufacturer of luxury (clothing) fabrics focusing on the high-income market in Africa, is no exception. Challenged by shrinking margins across the industry while preserving consistently the highest quality of production, remains the core of Vlisco’s business.
Balancing efficiency and quality
While a wide spectrum of levers could be applied to this challenge, it starts with one simple question. How to produce the required products in the most efficient way while still reaching & maintaining your quality standards? The answer to that is far more complex than to be captured in a few basic business rules. A challenge that Vlisco is trying to solve by using Machine Learning.
‘Predictive material input’ and ‘Production error detection’ and the challenges for Vlisco
With a complex production process, intensive labor activity and being located in the Netherlands, Vlisco deals with comparatively high labor costs. To optimize the effectiveness of its operation, Vlisco aims to significantly rely on Machine Learning to improve – “Predictive material input” and “Production error detection”. Both pursuing the goal of optimizing material usage.
The former, on the first look a fairly simple model. And yet, it heavily relies on the availability of production data as well as product & production order characteristics in order to correctly function. The latter, focussing directly on the efficiency and quality within the production process itself.
Image: Example of AI-supported anomaly detection at Vlisco
While anomaly detection has been a manual process in the past, Machine Learning opens up new opportunities. With support of Machine Learning, Vlisco is able to detect anomalies and defects by processing large numbers of production output quickly and consistently without tiring. And yet, to deliver the expected high quality to Vlisco’s customer, Machine Learning has to continuously prove its highest accuracy.
However, while the theoretical benefit might be obvious, Vlisco had to take several steps before even adopting Machine Learning. First, they had to design and set up their entire Machine Learning infrastructure. Second, their ambition to scale their ML application across their complete product catalogue, presented a further requirement for Vlisco. Third, company-wide acceptance is needed to fully use the potential in ML usage in their daily operations. Lastly, due to the continuous development of innovative new designs in their production process, AI models need to be trained by receiving feedback from Vlisco’s personnel.
Use case ‘Reduction of material excess’
- Ambition: Optimize required raw inputs for desired outputs of products to improve production costs
- Situation: Due to complexity and manual nature of production process, % of input materials ends up as scrap which increases cost significant
- ML model: input material estimation based on historical production data and order characteristics
- Potential future degradation of performance due to changing factory environment and designs
- Highly manual process and limited experience with ML models or applications
- ML infrastructure still in the early stages of set up
The solution: manageable AI supported by human feedback at Vlisco
As the desired AI models directly impact existing business processes, performance, explainability and corresponding trust were key for the adoption. Therefore, a close collaboration between humans and production machines was essential. An ideal opportunity for Deeploy.
In addition to providing a scalable platform for model deployment and management, Deeploy offers a unique feature: the human feedback loop. The feedback loop allows Vlisco’s business experts to directly evaluate and if necessary overrule every single prediction. Thereby, not only creating trust and transparency for experts and users but also giving real-time feedback for retraining of the AI models. Enabling a constant feedback loop. Thus, each prediction improves the estimation of how much material is required to produce a certain output directly influencing Vlisco’s production costs. To ensure sufficient model performance, Deeploy provides customized, real-time alerts, informing the Data Science Team about performance drifts and necessary corrective measures. Especially important if it comes to ensuring the highest accuracy for anomaly detection models. Based on the alerts, Vlisco’s team is able to improve and deploy new, improved models without risking any downtime.
Combined with automated audit trails, Vlisco is easily able to reproduce and document any prediction the model made, creating full accountability. All of that for each model in production as well as visualized in an simple, user-friendly interface.
Deeploy supports Vlisco as a solution that creates full explainability for every model, while simultaneously ensuring accountability and manageability. Ready to be scaled for new use cases and models!
Contact us to find out more about Deeploy, and how we could help you out.
Read another case
Banking: The Benefits of Explainability
Controlling Transaction Monitoring by implementing monitoring, explainability, traceability, and a h…
A collaboration between therapist, client and Artificial Intelligence for NiceDay The importance of…