COCOP: plant-wide monitoring and advisory tool for steel making process
A steel manufacturing plant-wide monitoring and advisory platform to reduce the number of surface and sub-surface defects at the final product, ensuring a good performance of the related sub-processes (secondary metallurgy, continuous casting and hot rolling).
Challenges:
Defects can be generated during Secondary Metallurgy, Continuous Casting and Hot Rolling sub-processes, but they are detected at the end of the manufacturing process.
To optimise each sub-process without a...
Type: Case study, Video, Poster, Presentation
CoPro: Thermal models for process optimisation in the canning industry
Thermal processing often constitutes the main bottleneck of the plant, consuming 70% of the total production time and 60% of the energy of a standard canning factory. Innovative solutions are needed to:
Minimise health risks derived from potential contamination by microorganisms.
Reduce product quality losses.
Increase efficiency by minimising production times and energy consumption.
Comply with environmental constraints
In attaining these objectives, thermal models are the essential...
Type: Software, Document, Poster
CoPro: Modelling concept and model library for large-scale optimisation in chemical plants
The Problem
Modelling is a major step in constructing optimisation-based solutions.
In large-scale optimisation of coupled chemical production sites, many models for plants and pieces of equipment have to be generated, implemented and maintained.
Many possible choices for the level of detail and the objective increase the necessary effort to implement optimisation-based solutions.
The Solution
Development of generic plant and equipment models of different modelling depth that can be...
Type: Other, Software, Poster
CoPro: Estimation of grey-box models with constraints
The Problem
Process models are the cornerstone for the successful deployment of advanced control and real-time optimisation routines.
Models often need to be customised with plant data to fit the actual processes, but fully replacing process knowledge by so-called deep learning is not a good idea.
Data-driven models often match plants just at the current or past operation but predict unphysical responses far from these.
The Solution
UVa developed a systematic methodology for grey-box modelling...
CoPro: Data-driven and hybrid modelling tool
The Problem
Data-driven modelling is attractive to obtain models which can be used to improve plant operations with a relatively low effort.
It is difficult to integrate data-driven modelling into traditional process simulation packages that rely on constructing flowsheet models from standard unit operation models.
Process engineers who want to use data-driven modelling commonly have to rely on custom modelling packages or general mathematical packages. These require investment of time and a...
CoPro: Surrogate modelling tool and workflow in gPROMS
The Problem
First-principles process models can offer high-fidelity predictions over wide operating ranges. However, they can be computationally complex.
This computational complexity can prohibit the use of these models for certain high-value applications, for example optimisation of integrated plant networks and other very large systems, online advisory systems and advanced control.
The Solution
Automatic derivation of surrogate models, usually in the form of explicit input/output relations...
CoPro: Model Management Platform
The Problem
Model-based real-time applications will increasingly be developed
– for different kind of applications and projects
– by different people
– with different model development tools
– in different versions.
To handle the increasing number of models, companywide model management and maintenance is necessary.
The potential for synergies when using models should be exploited better.
The Solution
LeiKon’s Model Management Platform.
Versioning and deployment of...
CoPro: Intexc Suite – Seamless integration of model-based real-time solutions into production IT environments
The Problem
Model based applications provide an important contribution to optimised plant operations.
It is still a challenge to integrate model-based real-time solutions with the existing heterogenous IT-systems in the plants.
Time and effort to integrate real-time model-based applications into IT-System environments must be reduced.
The Solution
The Intexc Suite – an integration platform for real-time data orchestration of distributed model-based applications in the process industries....
Type: Case study, Other, Software, Poster
CoPro: Optimisation of the operation of heat exchangers
The Problem
Heat exchangers are crucial elements for the reduction of the energy demand of the processing industry.
Heat exchangers often suffer from fouling, which decreases the heat transfer and thus the efficiency of the process.
Cleaning is needed to recover nominal efficiencies.
The optimal time for cleaning depends on the usage of the heat exchangers. Overall, these are many operation decisions difficult to take for the plant personnel.
The Solution
A methodology for monitoring the...
Type: Case study, Software
CoPro: Optimum operation of an evaporator network in viscose fiber production
The Problem
Recovery of the spinbath is the process with the highest energy demand in viscose production.
An evaporator network with 29 different evaporators is used for the reconcentration of the solution in different product cycles.
The efficiency of the evaporators depends on the type, volume flow rate, temperature and fouling effects.
The Solution
A decision-support system (DSS) for the assignment of evaporators to different product cycles was developed in a cooperation of Lenzing AG and TU...
CoPro: Large-scale production scheduling in the food industry
The Problem
Food process industries are typically characterised by the production of multiple products using flexible multi-stage facilities under tight operating and design constraints.
The optimal production scheduling of such a complex facility is a very challenging and demanding task, and existing solutions cannot generate schedules in computational times that are acceptable in industrial practice.
This complexity forces production engineers to derive production schedules that underutilise...
Type: Case study, Other, Software, Poster
CoPro: Optimal operation of sterilisation processes in food production
The Problem
Sterilisation is a crucial process in order to fulfill sanitary constraints in the food industries.
At Frinsa, the sterilisation process is performed in a set of parallel batch sterilisation units that are placed between continuous processing lines.
Being an energy-intense process, steam is a limited common resource for the sterilisers, and its availability influences their processing times.
Due to food safety constraints, there is a maxi mum waiting time for every sterilisation...
Type: Case study, Software, Poster