Warehouse Healing: Path Time Reduction through Intelligent Algorithms and the WMS SuPCIS-L8

In the midst of the age of digitalisation and automation, almost all logistics centres have one thing in common: the consistent use of data to derive recommendations for action or strategies is largely left by the wayside. The result: the often immense potential lies hidden and is rarely used.

The new warehouse slotting strategy "Warehouse Healing" defragments the warehouse and reduces the travel times for man and machine through the intelligent analysis of movement data and baskets of goods. As a result, the costs for the most labour-intensive process in a warehouse - order picking - are greatly reduced with little effort, which above all leads to performance increases and efficient resource planning in the warehouse. The realisation is very easy for the operative logistics: the warehouse management system SuPCIS-L8 suggests stock transfer and exchange processes for stocks and takes into account both classic pick frequencies, as known from ABC analysis, and the fact that a large number of articles are often ordered together(product affinity). Whether in off-peak times or by interspersing them into the regular daily business - these processes can be carried out easily and at any time. In the automated warehouse, on the other hand - for example in an automated high-bay warehouse (HRL) - these processes are carried out outside the normal shift.

Many companies are now dealing with the data in their systems and are not infrequently faced with the particular challenges: How do I select the right data sources and automation processes in the first place? Or, how do I derive company-specific use cases from it that offer real added value? And even if you have already successfully mastered these hurdles, you are still a long way off

‍

• Bring about concrete changes in the business processes and
• self-learning models and getting better and better results over time.

‍

With the innovation "Warehouse Healing" from S&P Computersysteme GmbH, customers can exploit the full potential from predefined use cases: from data collection to use in intralogistics, smart tools as well as experts from the data science team are available to the customer.

The concrete implementation of the use cases follows a simple, investment-saving principle and divides the introduction into two phases:

1. Proof-of-Value
   The first step is to validate the high benefit on the basis of customer data. Subsequently, the data sources are determined, the data integrated, transformed and subsequently visualised. Algorithms are then used to determine initial results (transfer and exchange suggestions) and, by interpreting the results, the savings in journey time specific to the use case are determined. The goal is to be able to make a data-driven decision for or against the introduction of "warehouse healing".
   
   
2. Implementation of the use case
   In the second phase, data integration is automated using cloud services. The results of the algorithms are now used to simulate healing processes and to defragment the warehouse beyond the normal level, without this having an impact on the ongoing business processes. At this point, the main objective is to create an optimised virtual target state that can be used to train the optimal combination of model parameters. The automatic training experiments in the background continuously improve the results. New in this phase is also the actual use of the results in the business processes and the direct interaction with the warehouse management system SuPCIS-L8. Communication takes place via an API. The customer can follow the realisation of the potentials in real time via progress indicators and enjoy the savings.

The strategy places special emphasis on a fast "time-to-value". This is achieved by using an algorithm to determine the stock transfers with the greatest effect and executing them first. After only a few hundred stock transfers, for example in multi-storey shelving systems, it is possible to save up to 60% travel time in the best case.

‍

By means of AI and simulations of changed model parameters, the result is constantly adapted to changing circumstances over time in order to minimise the sum of the outsourcing costs.

"With the innovative "Warehouse Healing" from S&P's "Warehouse Intelligence Suite", customers can transform existing data into business benefits. The strategy drastically reduces travel times and thus optimises the extremely labour-intensive process of order picking. The result: performance increases, optimal utilisation of workflows and efficient resource planning in the distribution centres."

By the way, the nicer thing about it is: this year, this topic was voted "Product of the Year 2021" in the software category by the intralogistics trade medium materialfluss!

Are you interested in the topic of Warehouse Healing and would like more information? Please feel free to contact us!

‍