F. Hecker

A case study on using evolutionary algorithms to optimize bakery production planning

The production of bakery goods is strictly time sensitive due to the complex biochemical processes during dough fermentation, which leads to special requirements for production planning and scheduling. Instead of mathematical methods scheduling is often completely based on the practical experience of the responsible employees in bakeries. This sometimes inconsiderate scheduling approach often leads to sub-optimal performance of companies. This paper presents the modeling of the production in bakeries as a kind of no-wait hybrid flow-shop following the definitions in Scheduling Theory, concerning the constraints and frame conditions given by the employed processes properties. Particle Swarm Optimization and Ant Colony Optimization, two widely used evolutionary algorithms for solving scheduling problems, were adapted and used to analyse and optimize the production planning of an example bakery. In combination with the created model both algorithms proved capable to provide optimized results for the scheduling operation within a predefined runtime of 15min.

Computer modelling and simulation of bakeries' production planning.

Computer simulations are used to represent the essential features of a real system so that analyzers can test their design skills in a convenient and safe environment. Organizations throughout the world are quickly moving to adopt process modelling and simulation as an integral part of their business decision-making and continuous improvement initiatives, due to their significant role in the design of a cost-effective system. ARENA fulfils these needs by mapping processes and simulating discrete and continuous systems. The properties of ARENA software engine involved in its ease of use and rapid mastery, power of complex system modelling, and open architecture to support user applications. This paper outlines how ARENA is applied to model, simulate and analyze the basic production processes. The case study is the bakerys production processes, at which the model creation is explained in detail and the simulation results are analyzed. This study gives a real-life example of how to use ARENA to model a complete production line in an efficient way.

Present Status of Automation for Industrial Bioprocesses

Abstract The pharmaceutical biotechnology, industrial biotechnology, and the food industries have been introduced to the Process Analytical Technology (PAT) initiative of the US Food and Drug Administration. The PAT, which is regarded as a milestone in the guidelines to efficient process control aims for sustained productivity and controlled batch-to-batch quality of products by measuring quality-related process variables. This is facilitated by a deeper understanding of the process and interconnection of process variables. Associated with deeper knowledge, the grade of automation may potentially be increased. In this chapter the fundamentals of automation, which are sensors, actuators, and open-loop and closed-loop control applications, are discussed for industrial bioprocesses. Because of the diversity of different bioprocesses and the different levels of knowledge about them, different approaches to automation have been used. Most applied systems are hybrid, combining different measurement techniques with various control methods. Soft sensors based on spectrometric measurements combined with proportional, integral or proportional, integral, derivative control are used most frequently. However application using Kalman filters and artificial neural networks for monitoring and heuristic control, fuzzy control, and model-predictive control are discussed in this chapter.

Image analysis and mathematical modelling for the supervision of the dough fermentation process

The fermentation (proof) process of dough is one of the quality-determining steps in the production of baking goods. Beside the fluffiness, whose fundaments are built during fermentation, the flavour of the final product is influenced very much during this production stage. However, until now no on-line measurement system is available, which can supervise this important process step. In this investigation the potential of an image analysis system is evaluated, that enables the determination of the volume of fermented dough pieces. The camera is moving around the fermenting pieces and collects images from the objects by means of different angles (360° range). Using image analysis algorithms the volume increase of individual dough pieces is determined. Based on a detailed mathematical description of the volume increase, which based on the Bernoulli equation, carbon dioxide production rate of yeast cells and the diffusion processes of carbon dioxide, the fermentation process is supervised. Important process ...