News & Events

No matter how well designed your production plants are – if your production schedules are not top-notch, you will lose time and money. Today, production scheduling is often done manually, which is tedious, expensive, and inefficient. Most approaches for the automatic generation of optimal production schedules have so far only had limited success in industrial applications.

Three years ago, the OptiProd.NRW consortium set out to develop a novel software tool for the automatic generation of optimal production schedules with a clear focus on its practical application. We were successful – the new tool lets you generate high-quality production schedules with the click of a button even for the most complex of plants. The tool achieves this by employing Digital Twins by INOSIM that are infinitely customizable to the complexities of industrial plants and thus lead to schedules that will just work – no need for expensive, error-prone, and time-consuming manual modifications.

On December 15, 2022, the OptiProd.NRW project held a public final workshop (both online and at the INOSIM offices in Dortmund). Its objective was to discuss the current state of the art of optimal production scheduling solutions and the challenges and benefits of their industrial deployment. The event was attended by almost 80 experts from potential end user companies of the OptiProd.NRW software, as well as engineering service providers and academic researchers. Impulse talks from leading industrial and academic experts from Bayer, BASF, and TU Dortmund provided different perspectives on the topic, and the OptiProd.NRW consortium gave an in-depth overview of their new simulation-driven software solution for the automatic generation of optimal production schedules that has been tailored to address the key challenges that arise in the industrial deployment of such solutions. The system was demonstrated on a complex industrial formulation plant of Bayer AG and other challenging industrial use cases.

Fueled by this overwhelming display of interest in the OptiProd.NRW scheduling software, INOSIM Group aims to commercialize the new solution within the near future, in close cooperation with project partner Bayer AG and other innovative producers. Be part of this exciting journey – contact us if you want top-notch scheduling of your production.

The publicly funded OptiProd.NRW project ran 3 years (from January 2020 to December 2022), and the project is funded with a total amount of around € 690,000, with € 420,000 provided by the European Regional Development Fund (ERDF) and € 270,000 by the German federal state of North Rhine-Westphalia.

Would you like to learn more about this project? Are you looking for an innovative SME as research partner? Please contact us.

No matter how well designed your production plants are – if your production schedules are not top-notch, you will lose time and money. Today, production scheduling is often done manually, which is tedious, expensive, and inefficient. Most approaches for the automatic generation of optimal production schedules have so far only had limited success in industrial applications.

Using Digital Twins by INOSIM, the OptiProd.NRW project has developed a new methodology and software tools for production scheduling. It allows generating high-quality production schedules with the click of a button even for the most complex of plants. And these schedules will just work – no need for expensive, error-prone, and time-consuming manual modifications.

On 15.12.2022, the OptiProd.NRW project, which will successfully conclude at the end of the year, will hold a public final workshop (both online and at the INOSIM offices in Dortmund) . The workshop provides a platform for interested industrial experts and researchers from the batch processing domain. It focuses on learning about the current state of the art of optimal production scheduling solutions and to discuss the challenges and benefits of their industrial deployment. Impulse talks from leading industrial and academic experts will provide different perspectives on the topic. The OptiProd.NRW consortium will give an in-depth overview of their new simulation-driven software solution for the automatic generation of optimal production schedules.This solution has been tailored to address the key challenges that arise in the industrial deployment of such solutions. The system is demonstrated on a complex industrial formulation plant of Bayer AG.

For more information, download the workshop invitation.

Please register for the workshop here – it’s free.

Using Digital Twins by INOSIM, the OptiProd.NRW project partners are developing a new methodology and software tools that let you generate high-quality production schedules with the click of a button, even for the most complex of plants. And these schedules will just work – no need for expensive, error-prone, and time-consuming manual modifications.

Fifth Consortium Meeting of the OptiProd.NRW Project

On August 27, 2021, the partners of the OptiProd.NRW project held their fifth consortium meeting via online conference to discuss the progress made since the last meeting in spring, to exchange new ideas, and to plan the next steps in the maturation, validation, and industrial application of the OptiProd.NRW tool for optimal production scheduling using detailed INOSIM simulation models.

The software system and optimization methodology have been extended and matured considerably over the last months, and we are now at the stage where we can demonstrate the power of the new methodology and software system on an industrially relevant scale. To this end, we have finished building a detailed INOSIM simulation model of a complex industrial formulation plant by partner Bayer that also includes the associated logistics processes (implemented in the new packaged-goods library of INOSIM). The model is currently validated in a real-world industrial setting, and we plan to start testing and demonstration of the system on the full-scale industrial model within the next months.

The first half of the project was all about methodological and prototypical development of the new OptiProd.NRW software system. While this work will continue also in the second half of the project, we will shift our focus to exploitation and commercial applications – besides industrial-scale testing and software maturation, we are developing a handbook, a toolbox, and guidelines that will enable us to apply the OptiProd.NRW approach quickly and efficiently to solve complex production scheduling challenges for our customers and thus add significant value to their operations.

Would you like to learn more about this project? Are you looking for an innovative SME as research partner? Please contact us.

Using Digital Twins by INOSIM, the OptiProd.NRW project is developing a new methodology and software tools for production scheduling. That will allow to generate high-quality production schedules with the click of a button even for the most complex of plants. And these schedules will just work – no need for expensive, error-prone, and time-consuming manual modifications.

In its first year, the project consortium has made large strides towards this ambitious goal: A full-scale prototype of the new software system has been created. The system rests on an innovative optimal scheduling methodology that was developed by leading researchers from TU Dortmund with support by the company Bayer and by the innovative SME INOSIM.

The project partners will present this new methodology and initial promising application results to an audience of leading researchers and practitioners at the Genetic and Evolutionary Computation Conference (GECCO’21) that will take place on July 10-14, 2021. The lecture is titled Simulation-based Scheduling of a Large-scale Industrial Formulation Plant Using a Heuristics-assisted Genetic Algorithm. It was co-authored by Christian Klanke (TU Dortmund), Dominik Bleidorn (INOSIM), Christian Koslowski (INOSIM), Dr. Christian Sonntag (INOSIM), and Prof. Dr. Sebastian Engell (TU Dortmund). The talk comes with a detailed scientific paper that will be published in the conference proceedings.

Do you have questions or want more information on OptiProd.NRW or our other research activities? Then meet us at GECCO’21 or contact us directly.

No matter how well designed your production plants are – if your production schedules are not top-notch, you will lose a lot of time and money. Using digital twins by INOSIM, the OptiProd.NRW project is developing a new methodology and software tools that let you generate high-quality production schedules with the click of a button even for the most complex of plants. And these schedules will just work – no need for expensive, error-prone, and time-consuming manual modifications.

In the first project year, the consortium has made large strides towards this ambitious goal. Partners TU Dortmund and INOSIM have built a full-scale prototype of the new software system for optimal production scheduling. The system is based on a new optimization approach that combines a tailored evolutionary algorithm with customized heuristics that are able to identify the most promising candidate solutions and that intelligently reduce the search space so that high-quality schedules can be found even for the most complex plants in reasonable time. And this algorithm now also supports campaign scheduling - it is able to automatically determine the best way to split your product demand into production batches so that your objectives and constraints are always met.

The software system includes a massively parallel simulation engine for INOSIM models – a key requirement for the efficient computation of optimal production schedules. The engine distributes simulation requests automatically to a large number of INOSIM instances and returns the results to the optimizer. The engine is currently running on high-performance servers at TU Dortmund and at INOSIM. Currently, we are achieving a 20-fold performance increase of the optimizer compared to single-instance simulation. And we are working on pushing the performance much further in the future.

Demonstrating the power of the new methodology and software system on truly industrial-scale use cases is a key goal of the project. We are about to finish building a detailed INOSIM simulation model of a complex industrial formulation plant by partner Bayer that also includes the associated logistics processes (implemented in the new packaged-goods library of INOSIM). The model represents the plant so faithfully that we expect the generated schedules to directly be applicable at the real plant. In addition, our master students Robin Ehrhardt and Engelbert Pasieka have built simulation models of other complex, more academic use cases that allow us to test the new tool on a variety of different scheduling challenges that regularly occur in industrial practice.

Fueled by the swift progress in the first project year, all project partners are looking forward to continue their work over the next months and years. We expect that we will be able to demonstrate the new system on the full-scale industrial use case in the near future, and we are hard at work to improve and generalize the prototypical implementations of the methodology and software tool into a mature solution for optimal production scheduling during the remainder of the project.

On June 16, 2020, the consortium of the OptiProd.NRW project held its second consortium meeting via online conference to discuss the progress made during the first 6 project months, to exchange new ideas, and to plan the next steps in the development of an efficient software tool for optimal production planning using detailed INOSIM simulation models.

Because of the large degree of enthusiasm of the project partners, all milestones were reached – and in some areas, work is ahead of schedule. Supported by the complete consortium, partner Bayer has finalized the definition and documentation of the central project case study, an industrial formulation process, that will be used to validate and demonstrate the OptiProd.NRW software system and that will ensure the industrial relevance and applicability of the project work.

Partner TUDO has developed an initial prototype for the meta-heuristic optimization with integrated systematic use of production scheduling heuristics and successfully demonstrated on a simple example process. The experienced researchers of partner TUDO are supported by the TUDO student Robin Ehrhardt. In his Master’s thesis project, he is developing a new approach for optimal production scheduling with INOSIM models applied to pipeless production plant in lab scale that is operated at TUDO for educational purposes and as a test bed for the validation and demonstration of production scheduling research results.

The software development work is making significant progress as well. The INOSIM simulation software was extended with a new interface for the integration of external software interfaces that enables the project partners to efficiently integrate their software prototypes with the core simulation software. In addition, work has started on the development of a software component that will enable massively parallel simulation directly within INOSIM – a key requirement for the efficient computation of optimal production plans for realistic case study with a high degree complexity.

All project partners are looking forward to continue their work over the next months and years with the same level of enthusiasm. Over the next months, the partners will develop detailed simulation models of the industrial case study and plan to create a first comprehensive prototype of the OptiProd.NRW software system that will be demonstrated on a simplified instance of the industrial case study towards the end of 2020.

On January 24, 2020, our employees Dr. Christian Sonntag, Christian Koslowski, and Tobias Storck welcomed representatives of TU Dortmund, Bayer AG, Projektträger Jülich, Evonik Technology & Infrastructure GmbH, and ARIC e.V. Hamburg at the INOSIM premises in the Dortmund technology park for the OptiProd.NRW kick- off meeting.

The partners presented their expertise and previous work and set the course for the project activities. The industry partners clearly pointed out the importance of the project: The current approach to production scheduling is largely manual and requires frequent adjustments, and the potential of using new software tools with innovative optimization methods is enormous.

In OptiProd.NRW, the partners are developing a new software system that employs state-of-the-art methods of mathematical optimization to automatically calculate optimal production schedules. Detailed "digital twins" of the production plant ensure that these schedules can be used directly in production without manual adjustments, which saves a lot of time and cost.

INOSIM contributes simulation models and a software framework for the systematic integration of optimization tools for production scheduling with these models. In addition, INOSIM will develop new features for its simulation software suites that will enable a massively parallel execution of simulations that will speed up not only optimization and production scheduling methods but also statistical analysis using INOSIM models. Partner Bayer contributes a realistic industrial case study, and partner TU Dortmund is responsible for the development of the optimization methodolgy and software. Evonik will provide industrial feedback from an end user perspective, and ARIC will support the consortium with innovation management and knowledge transfer.

Prof. Dr. Andreas Pinkwart, Minister for Economic Affairs, Innovation, Digitization and Energy of the German federal state of North Rhine-Westphalia, handed over the funding notices for eleven projects funded within the framework of the key market competition (Leitmarktwettbewerb) IKT on Wednesday,  January 8, 2020. The projects were selected from a total of 44 applications by a panel of industry experts. The funded projects include the OptiProd.NRW project that the INOSIM Software GmbH, headed by Dr. Christian Sonntag, is carrying out together with the Process Dynamics and Operations Group (DYN) of the Department of Biochemical and Chemical Engineering at TU Dortmund university, headed by Prof. Sebastian Engell, and Bayer AG Leverkusen. In the picture from right to left: Minister Prof. Dr. Pinkwart, Dr. Christian Sonntag (INOSIM Software GmbH), Dr. Manuel Remelhe (Bayer AG), and Prof. Dr. Sebastian Engell (TU Dortmund). © MWIDE NRW, M. Hermenau