Visualizing your Shipyard with Shipyard AI

Shipyard AI, ProModel’s dedicated shipbuilding application, continues to evolve and develop new capabilities – With five software releases in 2019, desired improvements in shipyard capacity management, optimization, scheduling and process engineering have been realized.   In addition, there has been a heavy emphasis on improving management’s ability to visualize shipyard production at both the strategic and tactical levels, at a single glance.

Building on a Strong Foundation

Historically, Shipyard AI has provided solid data and process information in highly detailed representations.  The application has included the following key visualizations, which we’ve continued to refine and improve over the years.

The Laydown map provides a top-down view of the entire shipyard with animation showing the progress of ship construction over time.

Image_syai-visualiaztion-article-laydown-map

Capacity Utilization Package (CUP) reports visualize resource utilization over time.

Image_syai-visualiaztion-article-cup-report

The Schedule screen features a Gantt chart representation of hull construction.

Image_syai-visualiaztion-article-schedule

The Unit Template Tree report shows a hierarchical breakdown of a hull into its component grand blocks, blocks, panels, etc.

Image_syai-visualiaztion-article-unit-template-tree

New Ways of Seeing the Shipyard

A recent emphasis on developing new types of visualizations is bearing fruit. This article introduces new ways of seeing the shipyard: the strategic Milestone Chart, the more tactical Location Resource View, and an updated Map Shapes editor.

Milestone Chart

A new Milestone Chart on the Hulls screen provides a strategic management view — visualizing the production of many hulls across long periods of time in a single view.

Image_SYAI Hulls Screen With Milestone Chart Nov 2019

Location Resource View

The Location Resource View report shows unit placements over time grouped by location.

This view allows you to interface with a unit and its dependencies in a single action, reducing the time needed and the possible introduction of errors. It provides a visualization of space in the shipyard over time to help you quickly make re-planning decisions.

Image_SYAI Location Resource View Report Nov 2019

Map Shape Editor

In an upcoming release, we’ll provide a map shapes editor to allow you to quickly add and edit unit shapes.

You can assign map shapes at the unit template level to have units appear on the Laydown Map with the correct shape.

Image_SYAI Map Shape Editor

See the What’s New Shipyard AI Webpage for more details on this year’s releases.

Process Simulator and ProModel Now Integrate with AutoCAD and Inventor by Autodesk

We are very excited to announce Process Simulator Autodesk® Edition and ProModel Autodesk® Edition.  Each product integrates with Autodesk® AutoCAD® and Autodesk® Inventor® to provide you a more valuable manufacturing plant design and process improvement capability.

For more information about Process Simulator Autodesk Edition, including videos, a downloadable pdf, and a 30-day evaluation copy go to the Process Simulator Autodesk Edition webpage.

For more information about ProModel Autodesk Edition, including videos, a downloadable pdf, and a 30-day evaluation copy go to the ProModel Autodesk Edition webpage.

If you are at the Autodesk University event this week (11/19-11/21) in Las Vegas stop by booth MFG210 to get a live demo and talk to our team.

Predictive Variables, Artificial Neural Networks and Discrete Event Simulation in Manufacturing

Rebecca Santos

Rebecca Santos ProModel Tech Support Engineer

During my Master’s program at BYU, I worked with a team to complete my thesis.  The work turned into a published article by the International Journal of Modelling and Simulation!  Since I work for ProModel, it’s only appropriate that I share it with my fellow simulation enthusiasts.  Please let me know what you think by commenting below.

Discrete event simulation (DES) is a powerful tool that can help users make better decisions. Over the years tools such as ProModel and Process Simulator have been developed to simplify the application of simulation, decreasing the learning curve and increasing its use. One of the advantages of simulation is that it is able to create lots of data with valuable information. However, the data analysis process can be challenging and relevant information may not be fully analyzed.

Observing the opportunity to more fully learn from the data, we decided to use data mining algorithms to help in the data analysis process, and more than that, to guide the modeler to the variables that most impact the outcome of the system being modeled.

The data mining algorithm picked was Artificial Neural Networks (ANNs) which has been good at learning from the data and making accurate predictions, according to the scientific literature. We applied ANNs to the data generated by the simulation model and we were able to create ANN models that could predict the simulation model results. The ANN models created were then interpreted and through the interpretation it was possible to rank variables according to their impact on the output results. This makes it possible for decision makers to know how to prioritize and where to place their investments.

Here is the abstract from the article:

This research used a discrete event simulation to create data on a shipment receiving process instead of using historical records on the process. The simulation was used to create records with different inputs and operating conditions and the resulting overall elapsed time for the overall process. The resulting records were used to create a set of predictive artificial neural network models that predicted elapsed time based on the process characteristics. Then, the connection weight approach was used to determine the relative importance of the input variables. The connection weight approach was applied in three different steps:

(1) On all input variables to identify predictive and non-predictive inputs

(2) On all predictive inputs and

(3) After removal of a dominating predictive input.

This produced a clearer picture of the relative importance of input variables on the outcome variable than applying the connection weight approach once.

You are welcome to access the published article at the journal’s website or the full original paper at the ProModel website.

 

Ingalls Develops Automated Unit Lay-Down ‘Advisor’ with Capacity Planning Tool

Image_Ingalls from theSigal MagazineHuntington Ingalls Industries – Ingalls Shipbuilding (Ingalls) identified substantial savings potential in the lay-down placement and assignment process that had been previously utilized for managing asset location throughout the construction process.

Building four different hull forms in the tight shipyard footprint is a challenge. Ingalls Shipbuilding work instructions define the processes and responsibilities for the proper allocation and optimization of real estate (lay-down spaces) for structural units and assemblies under construction, while providing forward visibility for scheduled or potential overloads to capacity.

However, the old capacity planning processes were tedious and overly time-consuming. Resulting real estate allocations were seldom optimal and often required substantial rework to resolve space allocation conflicts, as the construction schedules for each hull form jockey for the same production resources.

The Ingalls team developed an automated process that optimizes unit layout and scheduling, and increases the construction of many units under a covered structure, significantly improving production rates—a plus in the hot southern climate.

“The new tool has taken a process that historically took 10 weeks to complete and can now finish the scheduling activity in less than an hour. Following project completion and full system implementation, we expect to reduce ‘real estate’ allocation processing time by 30% and place 20 more units ‘under cover’ annually, with an estimated cost savings of over $990K per year.”

 (Article Courtesy of “theSignal” and DefenseNews.com)

Click here to read the rest of the Ingalls story

Whirlpool and The University of Michigan Collaborate on a Simulation Project Using ProModel Software

Embarking on a simulation project can seem like a daunting task at times, especially if the project must be completed above and beyond one’s normal responsibilities.  During those times, it is beneficial to consider engaging a partner to help.

Of course ProModel provides professional model building and consulting services, but another alternative is to partner with a University that teaches ProModel, MedModel or Process Simulator.  This type of industry | academia collaboration is a win-win for both organizations.

Please check out this very successful simulation project by Whirlpool on which they partnered with the University of Michigan. The article was published in PlantServices.com.

Click here to see a list of colleges and universities using ProModel software products.  If you would like more information about our academic program, please contact us at education@promodel.com or 801-223-4601.

 

 

From Reality to Model

Adjunct Prof Mark Klee Headshot

Mark Klee; Adjunct Professor – Eastern Kentucky University

I know what you are thinking “From Reality to Model” shouldn’t that be the other way around? As an engineer at Toyota for the past 24 years I often encounter manufacturing processes that have slowly de-optimized. And now, just by walking by the processes on the floor, I can see waste (motion, waiting, over-processing). I know this means that the these processes need some work.

Our typical method of improving these processes would be to employ the traditional Toyota Production System tools. We begin with observation and time study. Then we use video for motion analysis making these processes visual on paper with standardized work combination tables, standardized work charts, and production capacity calculations. Through these simple analysis tools, the waste in the process becomes more obvious and begins to generate ideas for improvement.

This is typically done one process or one zone of processes at at time. It is also usually done with paper, pencil, and stopwatch. The methods have proven time and again to be effective for process improvement and an effective method of developing engineers as well as manufacturing floor members in process improvement.

After the waste is discovered and the improvement ideas generated it is time to try some improvement ideas. The process visualization and capacity calculation documents are then modified to simulate the improvement idea. Then it is time to try the modified process on the production floor. The concept is tested in a controlled environment. After success is documented, the process standards are modified the team is trained to the new standard.

Using ProModel works very well with the Toyota Production System and as a method for developing manufacturing engineers, manufacturing floor members and students in manufacturing focused curriculum. In Eastern Kentucky University’s Applied Engineering and Management class, we follow this progression.

  • We first focus on learning process observation and visualization skill using the standard Toyota Production System tools.
  • Next we learn the processes of implementing controlled change in a mass production environment. We learn and practice these skills on the manufacturing floor to gain real world experience.
  • After learning the basics of observation and improvement, we come back to the classroom where we employ ProModel to fine tune our processes and learn if there are any opportunities for optimization that may have been overlooked.
  • With ProModel we can also test scenarios that may be difficult to test on the actual production floor like moving a piece of equipment, modifying a cycle time, changing a conveyor length or changing a delivery frequency.
  • These trials can be done as quickly as you can change the numbers in the model allowing for many more cycles of trial and error or trial and success in a shorter time.

As a result of the course and ProModel, students have deeper understanding of both the theory and application of process improvement allowing them to be an instant contributor to a manufacturing organization upon their graduation.

In the end, deeply understanding the current reality through observation, documentation, and modification of the current process helps us make a more accurate model. The result of the more accurate model is further optimization. This deepens learning and the improvement cycle continues.

Brief Bio:

Mark Klee, BS Eastern Kentucky University 1990, MS Purdue University 1992
Toyota Motor Manufacturing Kentucky 1994-Present
Eastern Kentucky University Adjunct Faculty 2012-Present

American Food Manufacturer Shows Packaging and Palletizing Improves Production and Plans for Growth with the Use of Simulation

CHALLENGES

An American food manufacturing facility was looking to buy a new palletizer for their packaging/palletizing floor. The manufacturing group needed to perform a capacity analysis of the 13 existing palletizers in the facility which supported 29 production lines. The company was facing challenges keeping up with consumer demand for their popular products. ProModel was brought in to build a pilot model of the packaging and palletizing floor.

OBJECTIVES

The first set of objectives were to analyze and understand the following elements of the current operations:

  1. Case type throughput for an eight-hour shift
  2. Packaging line downtimes
  3. Palletizer utilization

The next set of objectives involved analyzing the impact of different changes to the system:

  1. Cases per pallet
  2. Conveyor length
  3. Adjusting palletizer downtimes

SOLUTION

A ProModel consultant and the company’s personnel worked together to build a pilot model. Packing lines to conveyors to palletizers are represented in the simulation model shown below.

The diagram does not reflect the actual conveyor layouts, but by using data provided by the company, actual conveyor speeds and distances were taken into consideration. The conveyors and palletizers being considered for future expansion were also included in the model.

SS-Palletizer-Improvement_Image_3

More changes to the system can be analyzed since the simulation model is extremely customizable. For example, as additional downtime information is collected, the model can be dialed in to better reflect actual operations. The model allows for other process changes over time too like cycle times, introduction of new cases and new palletizers.

As a result of the success of the pilot model, this company and ProModel will be working together to model another palletizing floor of the facility. The one change that the client requested is that actual conveyor layouts be reflected in this second model to better illustrate how they impact production flow.

VALUE PROVIDED

The company has a model of each palletizing floor. These models can be connected and the organization can test and evaluate changes and expansions to the entire palletizing portion of their facility to guarantee that variations and increases in consumer demand will be met.