Warehouse Performance: Being smart and getting the most out of picking (part 4/4).

We come to the last part of the Warehouse Performance series. Parts 2 and 3 dealt with optimized stock reservation and batch planning. Both measures already ensure an enormous reduction in picking routes and times. In this article, we will go one step further and show how you can minimize travel times even more with intelligent product placement.

This is exactly where our newly developed strategy, "Warehouse Healing®", comes in. True to the motto: "Data is the new oil", data forms the raw material for the strategy in order to generate real added value. The aim is to identify existing patterns in the order history and use them to generate sensible stock transfer and putaway suggestions in order to minimize picking routes.

The actual implementation follows a simple, investment-friendly principle. But let's take a closer look at the individual steps of the strategy.

The first steps: Data collection and integration, followed by visualization and interpretation.
Before we can use the data and generate real added value from it, we need to identify it. This can be found in stock levels, topologies, article information, shopping baskets and movement data. Once the data has been collected and collated, it is visualized and interpreted.

The new "Warehouse Healing®" strategy defragments the warehouse. The intelligent analysis of movement data and shopping baskets reduces travel times for people and machines. Figure 2 shows the visualized data from step 1 of the strong warehouse fragmentation. Based on this recognizable situation, it is now a matter of analyzing, evaluating and recognizing patterns. This data forms the basis for the next phase. Model creation and training to generate real added value from the data.

‍Steps3 and 4: Model creation and training and application of the results
In the next step, the score of a storage area is defined. The lower the score, the more efficient the storage. A high score is achieved when items that have a strong affinity with each other are stored far apart. Or if items that are ordered frequently have a long picking route. Algorithms analyze the order history to identify stock transfers that lower the score. The results of the algorithms are used to simulate healing processes and further defragment the warehouse without disrupting ongoing business processes. First, an optimized virtual state is generated in order to train the optimal combination of model parameters. Automatic training experiments in the background continuously improve the results. Progress indicators allow the user to track the realization of the potential and enjoy the savings.

‍

Are you wondering whether the strategy is suitable for your warehouse? A potential analysis will show you how the "Warehouse Healing®" strategy will affect the warehouse area concerned. The strategy places particular emphasis on a fast "time-to-value". The algorithm determines the stock transfers with the greatest effect and implements these first. After just a few hundred stock transfers, you can save up to 40% of the travel time in multi-level shelving systems. Using artificial intelligence and simulations of changed model parameters, the result is constantly adapted to changing conditions over time. This keeps the total retrieval costs to a minimum. The strategy drastically reduces travel times and thus optimizes the extremely labour-intensive picking process. It is important for our data science experts to evaluate the results with you and discuss the expected benefits. Our experts provide you with a neutral assessment and support you in the decision-making process.

Your benefits in the course of applying the strategy: performance increases, optimal utilization of workflows and efficient resource planning in the logistics centers.

One of our customers tested the "Warehouse Healing®" strategy as a pilot project and introduced it due to the great results. Running a marathon in the warehouse? Not with Technilog. Store goods sensibly and reduce travel times.

‍
You would also like to make good use of your existing data? Feel free to contact us.‍