Dallmer relies on artificial intelligence for detailed production planning

AI makes complex production planning and detailed scheduling (PPDS) processes more transparent and increases adherence to deadlines

Authors:Maik Babucke, Head of the Dallmer GmbH & Co. KG order centerDr. Bernd Reineke, Managing Partner at A&K

Dallmer GmbH + Co KG specializes in the development and manufacture of products in the field of drainage technology. Founded over 100 years ago, the Sauerland-based company offers a wide range of products, including floor drains, shower channels, drainage systems for terraces and balconies and products for rainwater harvesting. Manufacturing technologies such as injection molding and mechanical production (e.g. turning, milling, grinding, polishing) as well as assembly activities by internal staff and external service providers are used to manufacture the products, most of which are made of plastic and steel.

Dallmer has the highest standards of functionality, design and quality not only for its products, but also for the internal processes in the cross-company supply chain, as a high level of availability and punctual delivery are at least as important. For this reason, Dallmer has been using an optimization tool for three years as an extension of the ERP functionalities in the planning and scheduling area. In addition, an AI-supported PPDS (Production Planning and Detailed Scheduling) was recently implemented for production and sequence planning. The aim was to replace the old, outdated detailed planning tool and thus increase both planning quality and the degree of automation.

The task of the new PPDS system is to enable an integrated view of quantities, capacities and required resources and to achieve an optimum planning result. Due to the high level of complexity with an unmanageable solution space, conventionally developed PPDS systems are not up to these requirements. It is therefore not uncommon to find systems in everyday operations that are only used to visualize the current production plan, which was created on the basis of comparatively less standardized parameters. Unfortunately, it never really takes into account all existing restrictions, because this still cannot be calculated in a reasonable time using conventional mathematical methods. The necessary computing power simply does not yet exist and will not exist in the foreseeable future. As a result, actual production almost always deviates from the target and planners often have to rely on the expertise of the production managers to ensure that they still meet the delivery readiness targets.


Score calculation for use in detailed production planning
© Anatoly-Stojko / DreamstimeArtificial intelligence enables Dallmer to get the most out of detailed production planning

However, Dallmer’s claim is different: the aim is to generate a weekly production plan that can actually be implemented, which already takes into account all known existing restrictions in production as well as the availability of the required resources such as machines, materials, personnel etc. and which can also be optimized to the current daily status at short notice in the event of new events.

To achieve this, AI should be used to take full account of the entire complexity of the production processes to determine the optimum result. However, AI alone is not enough. Other essential functionalities also had to be created in order to make AI usable. Essential building blocks are, for example

  1. Score functions for evaluating the solution scenarios and for mapping company-specific target values such as adherence to deadlines, productivity and throughput,
  2. a work plan model for precise and flexible mapping of production processes and
  3. a clear presentation of the planning result in the form of an interactive Gantt chart

The AI-based PPDS system now being used by SCT Supply Chain Technologies offers all these functions and specializes in finding the optimum in an almost infinite solution space. Even the medium-sized company Dallmer’s production processes are already enormously complex. During optimization, the AI algorithms recognize which changes, known as moves, lead to an improvement and which do not. All changes to the production plan are evaluated by the score functions and checked to see whether an improvement has been made. If this is the case, the previous solution is discarded and from then on the current solution is retained as the optimum until an even better solution is found. The AI recognizes in which direction the next moves should be made and which areas can be omitted. This means that it is not necessary to calculate all possible solutions, but only those that promise success.

Meeting deadlines comes first

AI-based PPDS vs. conventional detailed planning
The advantages of AI-based detailed planning systems over conventional PP/DS systems

At Dallmer, the greatest emphasis is placed on meeting deadlines when setting the score functions in order to ensure a high level of customer satisfaction. The second most important criterion is productivity, which manifests itself in the avoidance of set-up processes and machine downtimes. As in many other companies, it sometimes happens at Dallmer that a particularly important order is given priority over other orders. This can be realized via so-called external priorities, which are taken into account in the score calculation and lead to a better result when such orders are given preference.

The classic routing model, as is usually known from ERP systems, could not be used to map the work processes at Dallmer. For example, mapping the set-up processes in the plastics area was of great importance, as only specially trained personnel can be deployed for this. This set-up personnel must be given special consideration as a potential bottleneck during optimization. For this reason, the new AI-supported PPDS system uses a work plan model developed specifically for Dallmer, in which work processes can be divided into any number of work process sections, referred to below as tasks. This means that any processes can be displayed and any resources (e.g. set-up personnel, material, tools, etc.) can be assigned to each task. If alternative resources are available, these can also be easily defined for each task. This means that, for the first time, it is now possible to comprehensively check the availability of the required resources and implement the production plan in all respects.

The Gantt chart creates transparency

The interactive Gantt chart provides a quick overview of the planning result. The sequence of the individual tasks is displayed for each workstation. The dependencies between the tasks are also displayed as a graphical or tabular network structure. These network structures also reveal problem areas if, for example, a late material order prevents a task from starting on time. If the production controller wants to make a change to the plan manually, he can do this easily via a context menu. Not only are all possible placements of the task displayed, but also the evaluation of the shift using the score functions after the change. The production controller also receives a list of all other tasks that have been changed by his move. Using the integrated undo function, he can quickly and easily undo his intervention.

DISKOVER helps in times of changing bottlenecks

Evolution of PP/DS detailed planning
The performance of PPDS solutions has evolved over time. With AI, companies are now able to find the optimum in an almost infinite solution space for the first time

All in all, Dallmer was able to achieve excellent results in detailed planning within just a few months and significantly increase adherence to deadlines. “The new AI-supported PPDS system has become an indispensable tool, especially in times of changing bottlenecks, when suppliers are unable to deliver and staff are absent at short notice. It delivers better results faster despite increased complexity“, explains Maik Babucke, head of the order center at Dallmer. Users have come to appreciate the system in a short space of time and would not want to be without it. In a next step, external service providers will also be managed using this tool. Incidentally, Dallmer opted for the PPDS module of the DISKOVER APS system from SCT Supply Chain Technologies based on the recommendations of management consultants Abels & Kemmner, who also supported the implementation.

Maik Babucke summarizes: “In our continuous search for efficient solutions for production planning and control, we as a company have had outstanding experiences with SCT/Abels & Kemmner. The seamless integration of their advanced software has not only optimized our operational processes, but has also led to a significant increase in productivity. DISKOVER’s user-friendliness and intuitive interface enable a smooth workflow, while the flexibility of the system allows us to customize it to our specific requirements. SCT’s customer support has exceeded our expectations by always being responsive and solution-oriented. Regular updates ensure that the software is always up to date, and we appreciate the continuous development aimed at proactively anticipating customer needs. Our positive experience with SCT/Abels & Kemmner is reflected not only in the improved efficiency of our production processes, but also in the strengthening of our partnership with a company that is characterized by its innovative spirit and customer focus.”

Picture of Dr. Bernd Reineke

Dr. Bernd Reineke

Talk to us!

We are there for you personally and will be happy to advise you individually on our services and solutions.