Engineering Group is a global company headquartered in Italy, operating for over 40 years in the digital transformation sector. Simulation is one of the technologies they use to help businesses on their digital transformation journeys.
Engineering Industries eXcellence, or Engineering IndX for short, is the unit of the Engineering Group involved in this case study. The team focuses on manufacturing optimization and plant digitalization. They aid clients in modernizing their manufacturing processes with digital technologies. They manage design practices, supply and delivery planning, production, and collect data. Engineering IndX helps clients develop decision-support tools and apply them.
The case study end-client is a drilling power section manufacturer that produces different components for downhole drilling operations.
Problem
In general, the manufacturer deals with a highly intricate niche characterized by significant variability, which directly impacts production. This complexity comes from diverse factors such as the type of operations, drilling depth, materials being drilled, location, and the quality standards required for the components.
On the way to finding the best solution for manufacturing optimization, Engineering IndX defined two main challenges:
- Equipment upgrade evaluation: The R&D department aimed to introduce new equipment to enhance quality and initiate manufacturing optimization. So, the client needed a method to assess the impact of new equipment.
- Production scheduling organization: Each workstation operates independently, leading to suboptimal utilization of resources. The leadership wanted to improve operational management and plan the schedule.
The ultimate goal was to create a decision-support tool for all company employees. It had to help to evaluate:
- Potential plans for manufacturing optimization.
- Overall impact of introducing new equipment.
- Job completion based on current and anticipated shop floor work.
Solution
Engineering IndX initiated the project by creating a simulation of the drilling power section plant using AnyLogic software. The aim was to transition towards crafting a standalone decision-support tool, utilizing the foundation laid by this simulation model.
The AnyLogic model forms the system's backbone, capturing plant layout and manufacturing process logic in detail. Users can see live simulation runs and seamlessly navigate the model.
The client can run various scenarios, including both manufacturing optimization and non-optimization experiments. The decision-support tool produces output data and KPIs and visualizes them for the users’ convenience. The managers get valuable insights for decision-making and production workflow development.
The simulation-based decision-support tool design has several benefits:
- Usability: All the complexity of the back-end is hidden behind the app interface, so non-simulation engineers can use the tool seamlessly.
- Data Management: A Better process to manage data input and visualization.
- Scalability: Users can easily expand the solution to handle multiple scenarios and data sets.
Why AnyLogic?
Engineering IndX chose AnyLogic as the preferred simulation software for the client’s manufacturing optimization because of the tool’s versatile features and scalability. With AnyLogic simulation, engineers get an effective modeling tool for addressing customer-specific production processes.
The team needed software that adheres to object-oriented programming principles and helps to create a customizable data-driven model. The simulation must show manufacturing bottlenecks, provide useful insights for decision-making, and adapt to changes.
AnyLogic not only provides flexibility but also offers scalability to meet evolving organizational needs. It supports various deployment configurations, from single computer installations to cloud-based setups through AnyLogic Cloud.
Decision-support tool in action
When users open the tool, they encounter a login page. Then they are forwarded to the experiments area, where they select scenarios and choose the analysis type.
Decision-support tool interface: data input, scenario selection, and experiment configuration setup
After the experiment is set up, users move to the review screen, where they can set parameters and drag and drop new equipment to see how it might affect the processes. All changes they make are shown in the simulation model's plant layout.
Model output data for further decisions on manufacturing optimization (click to enlarge)
Results
Plant digitalization is a complex, multi-layered task, and simulation is an integral part of this process. As for the drilling power section plant case, Engineering IndX did a great job developing a custom decision-support tool that provides the plant employees with a simple solution for testing manufacturing optimization ideas. With the Engineering IndX solution integration, the end-client reached several milestones:
- Increased production and efficiency: With the decision-support tool, employees can now evaluate the impact of introducing new equipment and see how changes could affect production.
- Reduced scheduling time: Managers can create new schedules much faster, especially when disruptions occur. They can run experiments in the simulation-based tool and identify actions for manufacturing optimization and delay minimization.
- Improved customer service: Now, accurate job completion dates can be provided. Customers can receive more precise estimates of when to expect the final product.
But simulation implementation is just the first phase of a detailed roadmap that Engineering IndX has developed for the client.
- Wrap up the simulation implementation for the manufacturing optimization.
- Expand the logic to simplify adding new scenarios and data, adjust the user interface to answer additional questions, and run different simulations.
- Create a simulation-based digital twin. Сonnect the simulation model with near-real-time data from the shop floor, allowing customers to use the simulation for tactical and operational decision-making.
- Integrate AI. One of the main challenges for machine learning projects is having enough data to train algorithms and AI policies. Digital twins are effective in creating a comprehensive dataset.
At each step of the plant digitalization process, Engineering IndX was and is sure that AnyLogic is the right tool to support all the phases due to its flexibility and capability to adapt to new challenges.
The case study was presented by Matteo Percivale, a Simulation & Decision Science Practice Lead, and Luigi Manca, a Global Head of Simulation & Decision Science from Engineering Group, at the AnyLogic Conference 2023.
The slides are available as a PDF.
