Planimize’s advanced optimization tools are built on scientific innovations and supported by research published in peer-reviewed journals and international conference proceedings. Below is a selection of related scientific publications.
Planimize’s advanced optimization tools are built on scientific innovations and supported by research published in peer-reviewed journals and international conference proceedings. Below is a selection of related scientific publications.
Cluster tools are frequent in semiconductor manufacturing and generally, in high-mix settings, have chambers with different qualifications. Scheduling lots on cluster tools and assigning chambers to lots significantly impact factory efficiency. We propose an advanced optimization algorithm, embedded in a generic scheduling software, to manage areas with cluster tools instead of dispatching rules used in most software. Additionally, it considers many complex constraints, especially queue time constraints, while optimizing multiple objectives...
Scheduling decisions are critical in semiconductor manufacturing, especially in fully automated fabs. The Planimize Schedule Optimizer provides 24/7 real-time scheduling to steer activities in work centers such as photolithography and diffusion/cleaning. In the following, we present an overview of the algorithm and the real-world implementation of the software in production fabs.
Scheduling lots on machines is critical in semiconductor manufacturing because it impacts both factory efficiency and product quality. The Planimize Schedule Optimizer was then implemented to manage the increasing complexity of a growing fab, now exceeding 3,500 process steps across more than 200 resources. Significant improvements were achieved in comparison with the two previously used optimization engines, which were tailored to individual work areas. For instance, the number of wafers violating time constraints was reduced by 28%.
The following paper presents the challenges and results of implementing an optimization-based scheduling engine in a high-mix 300mm fully automated semiconductor manufacturing facility. Indeed, efficient scheduling of lots on photolithography machines is crucial due to their high cost and critical role in production. Therefore, optimally managing the transportation, storage and inspection of a large number of masks is essential to ensure this efficiency. Previously deployed in the cleaning and diffusion work center, the optimization engine was adapted for photolithography and is operational since May 2024.
The following paper surveys the industrialization of an advanced optimization engine that was developed by Planimize and put into production in the cleaning and diffusion work center of the most advanced factory of a semiconductor manufacturing company since 2023. Hundreds of lots requiring several thousands operations in the work center must be scheduled on about 150 machines, while taking complex constraints into account, in particular hundreds of time constraints, and optimizing a collection of criteria. The optimization engine provides significantly better results, runs significantly faster, and can handle much larger problem instances than Constraint Programming optimization engine previously used in the factory.
A. Bitar, S. Knopp, K. Tamssaouet (Planimize), L. Delcloy and R. Roussel (STMicroelectronics, Crolles)
The flexible job shop scheduling problem (FJSP) is an NP-hard combinatorial optimization problem, which has wide applications in the real world. The complexity and relevance of the FJSP have led to numerous research works, especially on its modeling and resolution. The following summarizes the research of the past 30 years on the problem, by presenting and classifying the different criteria, constraints, configurations and solution approaches that have been considered. Recent emerging topics on complex shop scheduling, multi-criteria optimization and uncertain and dynamic environments are also discussed. Finally, future research opportunities are proposed.
Tamssaouet.K, Dauzère-Pérès, S., Knopp, S., Bitar, A., & Yugma, C.
In the following, we study a scheduling problem on non-identical parallel machines with auxiliary resources and sequence-dependent and machine-dependent setup times. Three different criteria are defined and analyzed altogether: The number of products completed before the end of a given time horizon, the weighted sum of completion times and the number of auxiliary resource moves…
Bitar, A., Dauzère-Pérès, S., & Yugma, C.
The following paper addresses the job-shop scheduling problem in which the machines are not available during the whole planning horizon and with the objective of minimizing the makespan. The disjunctive graph model is explicitly used to represent job sequences and to adapt and extend known structural properties of the classical job-shop scheduling problem to the problem at hand. These results have been included in two metaheuristics (Simulated Annealing and Tabu Search) with specific neighborhood functions and diversification structures.
Tamssaouet, K., Dauzère-Pérès, S., & Yugma, C.
We consider a Flexible Job-Shop Scheduling Problem (FJSP) with batching machines, re-entrant flows, sequence-dependent setup times and release dates while considering different regular objective functions. Semiconductor manufacturing is undoubtedly one of the most prominent practical applications of such a problem. Existing disjunctive graph approaches for this combined problem rely on dedicated nodes to explicitly represent batches. Comparatively, to facilitate modifications of the graph, our new model reduces this complexity by encoding batching decisions into edge weights…
Knopp, S., Dauzère-Pérès, S., & Yugma, C.
In the following paper, we propose a metaheuristic for solving an original scheduling problem with auxiliary resources in a photolithography workshop of a semiconductor plant. The photolithography workshop is often bottleneck, so improving scheduling decisions in this workshop further improves indicators of the whole plant. Consequently, we consider two separate optimization criteria: the weighted flow time (to minimize) and the number of products that are processed (to maximize)…
Bitar, A., Dauzère-Pérès, S., & Yugma, C.
Winter Simulation Conference - 2020
Le Quéré, É., Dauzère-Pérès, S., Tamssaouet, K., Maufront, C., & Astie, S.
Winter Simulation Conference - 2018
Tamssaouet, K., Dauzère-Pérès, S., Yugma, C., Knopp, S., & Pinaton, J.
Proceedings of the Winter Simulation Conference - 2014.
Knopp, S., Dauzère-Pérès, S., & Yugma, C.
Proceedings of the Winter Simulation Conference - 2014
Bitar, A., Dauzère-Pérès, S., & Yugma, C.
Cluster tools are frequent in semiconductor manufacturing and generally, in high-mix settings, have chambers with different qualifications. Scheduling lots on cluster tools and assigning chambers to lots significantly impact factory efficiency. We propose an advanced optimization algorithm, embedded in a generic scheduling software, to manage areas with cluster tools instead of dispatching rules used in most software. Additionally, it considers many complex constraints, especially queue time constraints, while optimizing multiple objectives.
Scheduling decisions are critical in semiconductor manufacturing, especially in fully automated fabs. The Planimize Schedule Optimizer provides 24/7 real-time scheduling to steer activities in work centers such as photolithography and diffusion/cleaning. In the following, we present an overview of the algorithm and the real-world implementation of the software in production fabs.
Scheduling lots on machines is critical in semiconductor manufacturing because it impacts both factory efficiency and product quality. The Planimize Schedule Optimizer was then implemented to manage the increasing complexity of a growing fab, now exceeding 3,500 process steps across more than 200 resources. Significant improvements were achieved in comparison with the two previously used optimization engines, which were tailored to individual work areas. For instance, the number of wafers violating time constraints was reduced by 28%.
The following paper presents the challenges and results of implementing an optimization-based scheduling engine in a high-mix 300mm fully automated semiconductor manufacturing facility. Indeed, efficient scheduling of lots on photolithography machines is crucial due to their high cost and critical role in production. Therefore, optimally managing the transportation, storage and inspection of a large number of masks is essential to ensure this efficiency. Previously deployed in the cleaning and diffusion work center, the optimization engine was adapted for photolithography and is operational since May 2024.
The following paper surveys the industrialization of an advanced optimization engine that was developed by Planimize and put into production in the cleaning and diffusion work center of the most advanced factory of a semiconductor manufacturing company since 2023. Hundreds of lots requiring several thousands operations in the work center must be scheduled on about 150 machines, while taking complex constraints into account, in particular hundreds of time constraints, and optimizing a collection of criteria. The optimization engine provides significantly better results, runs significantly faster, and can handle much larger problem instances than Constraint Programming optimization engine previously used in the factory.
Bitar, A., Knopp, S., Tamssaouet, K. (Planimize), Delcloy, L. & Roussel, R. (STMicroelectronics, Crolles)
The flexible job shop scheduling problem (FJSP) is an NP-hard combinatorial optimization problem, which has wide applications in the real world. The complexity and relevance of the FJSP have led to numerous research works, especially on its modeling and resolution. The following summarizes the research of the past 30 years on the problem, by presenting and classifying the different criteria, constraints, configurations and solution approaches that have been considered. Recent emerging topics on complex shop scheduling, multi-criteria optimization and uncertain and dynamic environments are also discussed. Finally, future research opportunities are proposed.
S. Dauzère-Pérès, J. Ding, L. Shen, K. Tamssaouet
The following paper surveys the industrialization of an advanced optimization engine that was developed by Planimize and put into production in the cleaning and diffusion work center of the most advanced factory of a semiconductor manufacturing company since 2023. Hundreds of lots requiring several thousands operations in the work center must be scheduled on about 150 machines, while taking complex constraints into account, in particular hundreds of time constraints, and optimizing a collection of criteria. The optimization engine provides significantly better results, runs significantly faster, and can handle much larger problem instances than the previous Constraint Programming optimization engine used in the factory.
K. Tamssaouet and S. Dauzère-Pérès
In the following, we are concerned with the resolution of a multi-objective complex job-shop scheduling problem stemming from semiconductor manufacturing. To produce feasible and industrially meaningful schedules, the following paper extends the recently proposed batch-oblivious approach by considering unavailability periods and minimum time lags and by simultaneously optimizing multiple criteria that are relevant in the industrial context. A novel criterion on the satisfaction of production targets decided at a higher level is also proposed.
Tamssaouet, K., Dauzère-Pérès, S., Knopp, S., Bitar, A., & Yugma, C.
In the following paper, we study a scheduling problem on non-identical parallel machines with auxiliary resources and sequence-dependent and machine-dependent setup times. Three different criteria are defined and analyzed altogether: The number of products completed before the end of a given time horizon, the weighted sum of completion times and the number of auxiliary resource moves.
Bitar, A., Dauzère-Pérès, S., & Yugma, C.
The following paper addresses the job-shop scheduling problem in which the machines are not available during the whole planning horizon and with the objective of minimizing the makespan. The disjunctive graph model is explicitly used to represent job sequences and to adapt and extend known structural properties of the classical job-shop scheduling problem to the problem at hand. These results have been included in two metaheuristics (Simulated Annealing and Tabu Search) with specific neighborhood functions and diversification structures.
Tamssaouet, K., Dauzère-Pérès, S., & Yugma, C.
We consider a Flexible Job-Shop Scheduling Problem (FJSP) with batching machines, re-entrant flows, sequence-dependent setup times and release dates while considering different regular objective functions. Semiconductor manufacturing is undoubtedly one of the most prominent practical applications of such a problem. Existing disjunctive graph approaches for this combined problem rely on dedicated nodes to explicitly represent batches. Comparatively, to facilitate modifications of the graph, our new model reduces this complexity by encoding batching decisions into edge weights…
Knopp, S., Dauzère-Pérès, S., & Yugma, C.
In the following paper, we propose a metaheuristic for solving an original scheduling problem with auxiliary resources in a photolithography workshop of a semiconductor plant. The photolithography workshop is often bottleneck, so improving scheduling decisions in this workshop further improves indicators of the whole plant. Consequently, we consider two separate optimization criteria: the weighted flow time (to minimize) and the number of products that are processed (to maximize)…
Bitar, A., Dauzère-Pérès, S., & Yugma, C.
Winter Simulation Conference - 2020
Le Quéré, É., Dauzère-Pérès, S., Tamssaouet, K., Maufront, C., & Astie, S.
Winter Simulation Conference - 2018
Tamssaouet, K., Dauzère-Pérès, S., Yugma, C., Knopp, S., & Pinaton, J.
Proceedings of the Winter Simulation Conference - 2014.
Knopp, S., Dauzère-Pérès, S., & Yugma, C.
Proceedings of the Winter Simulation Conference - 2014
Bitar, A., Dauzère-Pérès, S., & Yugma, C.
