Supermarkets are heavily impacted by unexpected peaks in demand and product unavailability from areas that have been affected by the COVID-19 pandemic. This global health crisis has uncovered vulnerabilities in our food supply chains, affecting the capacity of food retailers to ensure its continuity. It is critical for retailers to quickly respond to these sudden changes, but many struggle with this because their planners still rely on spreadsheets and legacy tools to plan their logistics operations.  

These methods aren’t made to solve today’s complex supply chain planning challenges. The methods can indicate how well plans have been executed, but lack the capability to help manage unforeseen challenges on current operations and in the future.

Fortunately, there are solutions available that can help retailers cope with disruptions. Planning and optimization software, powered by mathematical optimization, can perform calculations based on all available data sources to generate optimal plans It will help your planners manage existing resources and constraints to meet your business goals.

The right software, such as DELMIA Quintiq, can empower retailers to adjust to a new set of constraints and requirements in real time such as:

• New pick-up locations
• Sudden changes in volume
• New or additional modes of transport
• Changes in network of stores
• Traffic congestion

Here’s a recent example of how DELMIA Quintiq enabled a large European retailer to efficiently respond to availability issues caused by the COVID-19 pandemic:

Recent developments have signaled that the time has come for retailers to take their supply chain agility to the next level. Download this PDF to discover how a planning and optimization system can help you deal with today’s disruptions and tomorrow’s challenges.

Continue the discussion by clicking here to learn more about our smart solutions for logistics planning.

Part 3 of a 3-Part Series on Airports by Isaac Benzaquen and Jerry Schwinghammer

As mentioned in previous blogs, the Virtual Twin is the link between virtual and physical environments. Virtual twin is becoming increasingly to create a smart airport.  The smart airport can be described as a system of systems that are encountered throughout the passenger journey. Each system works to deliver services.  By connecting all these systems, it provides a holistic view of the end to end passenger journey by connecting the dots between:

• Landside and air-side functions
• Airport, airlines and passengers’ needs
• All the passenger journey touch points

These systems together act as the airport’s intelligent nervous system. The foundation is built on a well-defined systems engineering methodology called Model-based Systems Engineering (MBSE). This discipline is found in numerous industries and proven to be effective.    

Integrating an airport’s siloed systems through a systems approach, enables executives to ensure that their vision permeates the entire enterprise in a harmonious and agile manner. As airports strive to be more businesslike in their operations it is key that decision making is fundamentally aligned to customer needs. The complexity of an airport creates significant challenges when not approached from a systems perspective. Taking a top-down customer centric systems engineering approach yields better, more deliberate results. Through systems thinking, innovation can be instilled cohesively throughout the organization.   

The complexity of an airport creates significant challenges when not approached from a systems perspective.

Specifically, a systems approach is inherently top-down starting from a clear and simplified, high-level view of an airport’s mission. Such as a “Deliver a highly customer-centric delightful traveling experience.” This vision is then driven down into detailed sub-systems that must conform to the larger vision of highly quality passenger experience. Decision-making must continually drive toward that vision at all levels.

Systems Thinking

In traditional design, we go too much into technical details, we jump into the solution before properly considering the problem, or stay at too high a management level, and we become blind on how the product will be used. We spend most of our time in integration, and test phases to ensure that the system behaves properly.

MBSE focuses on defining passenger needs and required functionalities early in the development cycle. Then it takes into consideration the required functionality in all the phases of the airport’s life, from design concept to detailed development, Operation, maintenance, and finally decommissioning.

Systems Engineering considers both the business and the technical needs of the airport with the goal of providing a quality product or service that meets the passenger needs.  Risks are identified and mitigated in early phases because of the systematic and holistic approach of systems engineering. Each change is simulated within the system as early as possible so that all the events or situations are addressed.  The net result is faster decision making, lower risk and a better service or product. 

This approach allows for rapid adaptation to new, potentially disruptive technologies. The airport’s master plan is a great place to start applying systems engineering to ensure designs and changes drive toward a common vision and improve passenger experience.

This article is part of a series of articles on how to explore, develop, and adopt virtual twin technology to move the airport industry forward.  Read Part 1 here: https://blogs.3ds.com/delmia/a-practical-look-at-bringing-innovative-digital-and-virtual-twin-technology-to-airports/ and Part 2 here: https://blogs.3ds.com/delmia/five-ways-a-virtual-twin-can-benefit-an-airport/

Part 2 of a 3-Part Series on Airports by Isaac Benzaquen and Jerry Schwinghammer

Tomorrow’s airport cannot be achieved with yesterday’s solutions. With today’s old airport technology, the challenges will be difficult to overcome. In all the pressures an airport is experiencing it is important to see these challenges as an opportunity to significantly change for the better. As mentioned in a related article, the Virtual Twin is the link between virtual and physical environments. Virtual Twin technology is on the scene for many industries and delivering value and return. Embracing this new virtual twin technology will enable airports to achieve their innovation goals. 

The virtual twin encapsulates the overall airport’s life cycle. There are five elements where a virtual twin is of benefit to airports.   

1. Ideation

Airports are continuously seeking for new ideas to make airports more than infrastructures, but real living places. One of the routes to improving the journey is by creating a 3D virtual experience, simulate the idea and validate its benefits. This 3D virtual experience can then be used to communicate with airport stakeholders to secure necessary capital funding. The value proposition is that stakeholders have higher confidence early on that money will be spent wisely and the decision cycle can be radically shortened from years to weeks. 

2. Design and Engineering

The Virtual Twin provides a collaborative environment to federate all supplier deliverables around a unique 3D mockup to converge much faster on final design. Then verify and validate the subcontractors design conditions and physical dimensions. The conformance of the final 3D design to initial requirements and FAA regulations can be readily shown. Tenants will benefit from a better controlled process and can achieve on plan, on cost, on time delivery. Failure to do so will increase design cost and reduce design quality of the terminal, which will increase overall airport CAPEX and OPEX.

3. Construction

By leveraging the Virtual Twin, project delivery teams are able to simulate how construction or renovations impact airport operations. The overall operational impact of taking major infrastructure out of service, such as a terminal, can be simulated. Once evaluated then an effective and proactive operational plan can be put in place to minimize disruption. 

4. Sales and Marketing

There are many opportunities for marketing opened up by the Virtual Twin.  The first is to entertain and make the passenger’s journey more enjoyable. The second one is to increase revenue. The third opportunity is to bring innovations into improving passenger experience.

There are many opportunities for marketing opened up by the Virtual Twin. 

The passenger’s journey is made more enjoyable by leveraging the virtual twin to create AR and VR applications. Airports can increase revenues by being able to create a virtual shopping experience. Marketing can validate the passenger experience elements as well as explore new innovative concepts in a virtual environment. Additionally, employing Virtual Twin eliminates the need for real photo shoots and costly film sets for a new marketing campaign.

5. Operations (Maintenance and passenger flow)

There are two primary operational roles for the Virtual Twin – Maintenance and Operations.

In the maintenance field the Virtual Twin provides a platform to monitor and analyze sensor information to predict an asset failure. Further, it provides a diagnostic tool by simulating what went wrong. All this information is captured and communicated in 3D to the field via the Work Order to accelerate investigation and reduce maintenance costs.  

In the Operations arena the simulation in 3D provides a better understanding for daily operations. It provides a holistic, 3D view on how planning interacts with airport activities such as construction, renovation or other events which may cause irregular operations. Mitigation scenarios can be simulated to address the impacts and shorten times to recovery. This avoids costs and delays such as turn-around times and most importantly congested passenger flows.  It will be imperative that the virtual model provides a reasonable and trustworthy representation of what would happen in real life.  

This article is part of a series of articles on how to explore, develop, and adopt virtual twin technology to move the airport industry forward.  Read Part 1 here: https://blogs.3ds.com/delmia/a-practical-look-at-bringing-innovative-digital-and-virtual-twin-technology-to-airports/

Effectively running and maintaining a successful warehouse in the modern supply chain is increasingly challenging. New processes and innovations continue to reinvent the world of logistics.

Implementing something as simple as barcode scanning can completely transform your inventory management system.

Barcoding

Barcodes have developed from an early innovation to a nearly mandatory tool for inventory optimization and management. Their design offers the storage of information in a compact and easy to access form. Just a simple code scan can provide access to a wealth of information in the time it takes to blink.

These systems require barcode labels or tags to be affixed to bins or individual inventory parts. In addition, a scanner must be used to log information.

Software

Coupled with inventory management software, the codes become an extremely effective tool. Modern software options are simple to use, but powerful enough to accomplish complex tasks.

E-commerce platforms can be updated in real-time with current inventory levels. While most systems will show you when inventory is low, some will even re-order goods from suppliers when inventory levels dip beneath a specified threshold.

Access to Information

Quality of information is even more important than quantity. While having a ton of data at your fingertips might sound great, if it is not accurate then it is useless. Decisions are only as effective as the data and information they are based on.

Maintaining clear and accurate records in any inventory or asset management is vital to the success of the system. Faulty or inaccurate information defeats the purpose.

Conclusion

The only way to stay current in the constantly evolving supply chain is to adapt. Adopting technologies which will improve efficiency and provide highly detailed and accurate data is a must. Barcode scanning is a must for current organizations.

The key to adopting new systems and supply chain technologies is to ensure they fit your organization. It doesn’t make sense to implement a new system if it will simply cause more problems than the utility it will provide.

Technology has never been so present in our lives. Despite that, the truth is that concepts such as human-machine connectivity, realistic simulation, Artificial Intelligence, and 3D experiences, all essential to the new times, are just beginning to become more relevant and present in corporate routines.

In 2020 however, we had a pleasant surprise: the Brazilian Carnival had the last word in technology, with Rosas de Ouro samba school taking the history of industrial revolutions with emphasis on the industry renaissance that we are living here in Brazil.

The main idea of ​​the “Tempos Modernos” (Modern Times) * storyline, developed by carnival artist André Machado, was to show, through the history, the arrival of this new era. The goal was to present to the general public the innovations that can transform people’s lives, offering more productivity and efficiency in our daily lives.

Technologies from different vendors was widely used in costumes and allegories to show how digital innovation can transform areas such as health, agriculture, food and urban mobility, among many others. FEI University Center, a partner of Dassault Systèmes, for example documented one of the floats present in the parade. This means that the entire structure of the float was be digitized and rebuilt into a 3D model to enhance its physical construction.

Visionary, the Rosas de Ouro Society, a traditional São Paulo association, has always embraced themes that carry a message or leave a warning to society. “Tempos Modernos” will be the flag raised by the school in the parade of this year. It is an extremely important cause that should be observed by everyone with attention, including ordinary people, influencers, members of civil society, businesses, governments and experts. After all, we are living a unique moment in our history, with the technological revolution making room for a complete change in the way we live, work and relate.

It is very important for society to be able to promote and inspire the discussion about the future, enabling the understanding of the advances that are happening. Not to mention the importance of getting ready to fully exploit the advantages that technology can bring to our lives. At the same time, we have to work and identify the actions needed to truly create a Brazil able to take full advantage of the opportunities offered by innovation in all its forms.

We are heading for the biggest transformation in history, with changes happening from factories to the way we manage our children’s schedules at school. We are facing a new paradigm in which everything we consume and do will be different. Therefore, although this is not the first industrial revolution lived by mankind, it is almost unquestionable that it will be the most striking, with structural changes in our lives.

This becomes evident, for example, when we observe that innovation is at the heart of industries and businesses, completely transforming the way they work and develop their products and services, enabling the creation of new business models that can completely change the balance of business forces in competitive markets. The universe of possibilities is huge.

Production lines in Brazil could be directly run by operations in China, which could receive projects submitted by a team located in Europe. This means that factories will have new digital connectivity present at all stages of their processes, making them more efficient, flexible, faster and transparent. Service companies and homes will follow this model, becoming increasingly intelligent.

With new technologies, geographical barriers will definitely disappear and partnerships between universities and companies will have an extremely positive global impact, and therefore can prepare young Brazilians for a new and emerging international job market. This digital connection could be the basis for improving the transmission of knowledge among people, guiding and preparing new talent for the future.

Successful professionals in this new phase will be able to quickly develop skills to work in new digital environments. According to a global study of more than 2,000 companies from 26 countries including Brazil, world leaders in the industrial sector intend to invest 5% of all annual revenues in digitizing key functions for their companies, almost $ 1 trillion by 2020. The main focus of these investments will be 3D solutions, manufacturing systems, sensors and connectivity devices.

Emerging economies such as Brazil can benefit from this moment of innovation and change to reach higher levels of efficiency and global market participation. Technology has been driving the growth of wealth in many countries and this can also be replicated in the case of Brazil. With these innovations it will be possible to develop new products, expand business and generate a wave of jobs, with professionals prepared to work in new roles.

Investing in knowledge and technology will always be a differential. It is very interesting to have such a bold proposal for Carnival, which is the biggest cultural event in Brazil. Undoubtedly, the paradeis already equipped with the latest in technology. Now it lacks for the Brazilian society to prepare itself to immerse in this new digital environment.

Translator´s note: *Based on Modern Times, film of Charles Chaplin, theme of Rosas de Ouro Samba School for the 2020 Carnival Parade.

Continue the conversation and learn more about DELMIA Robotics in our DELMIA Robotics community. https://r1132100503382-eu1-3dswym.3dexperience.3ds.com/#community:48/blog

Part 2 of a 2-part series

In case you missed it, check out Machine Learning Overview, Part 1 in our DELMIA Blog.

Unsupervised Machine Learning

In contrast to supervised Machine Learning, unsupervised machine learning doesn’t have any monitoring or teaching system. We let the machine to figure out its own model from unlabeled data.

In figure 2 the data set consists of ‘n’ images of cats and dogs but now this image is unlabeled (means we don’t mention their tags to learning system), for instance, in figure 2 now Image 1 is unlabeled it may be cat or dog. Likewise, there will be ‘n’ unlabeled images from 1 to n.

So, to tackle this unsupervised learning system uses the concept of clustering. Clustering is a grouping technique in which similar featured objects are grouped together. In the above example figure 2, we have two different categories (cats vs dogs). We design our learning system capable of clustering into two groups of images separately. We achieve this by the concept of feature selection in other words similarly in images are grouped together and dissimilar images group together.

Reinforcement Learning

Reinforcement learning is a special type of machine learning especially used for game theory, signals and system and control systems.

In reinforcement learning, whenever the environment is sending the information to the learning system, its output values and critic will comment on those values. For instance, if the output is appropriate for the machine then it will reward the learning system to perform the next task through actions. However, if the output is erroneous it punishes learning system and sends a single through actions to repeat the same task with the different data point.

Likewise, it checks every point in the environment to get the reward from the critic. This process of validating every single point will consume huge memory, time and require high computation speed. This is a major drawback of reinforcement learning. However, machine learning researches are still working on it to compensate for these issues and to create much more cost-efficient systems. Hopefully in the near future we able to see one.

What’s Next

Most Machine Learning algorithms fall under these categories, but current advancement in machine learning created many more different algorithms, such as Semi-Supervised Learning.

Why and Where We use Machine learning

According to this Forbes article, Machine Learning is going to a common buzzword in Medical, Finance, Transportation, E-commerce and many more sectors. But why are popular companies focusing on machine learning nowadays? The answer is because of the Machine Learning capabilities.

Part 1 of a 3-Part Series on Airports by Isaac Benzaquen and Jerry Schwinghammer

Virtual Twin technology is already an imperative for many industries and delivering value and return. Airports should evolve beyond Geographic Information System (GIS) from analytic to holistic decision making. 

As an early technology pioneer, Jerry implemented a GIS system in Orlando International Airport. The technology was just emerging on the scene and the value propositions were aspirational at best. A cool looking map was interesting, but not enough. It wasn’t until the program focused on “actionable data” that progress was made. The GIS program paid for itself many times over and became a central part of the planning processes at the airport. The next evolution to holistic decision making and simulation remained just out of reach. New tools, technology, and new approaches were needed.

In many industries holistic decision making is now real thanks to 3D spatially enabled tool sets.  Today, decisions must be made much faster and with greater confidence to meet growing challenges.  In order to adapt to the complexity, there is a fundamental shift from linear thinking (analytics) to systems thinking (innovation) that underpins the value proposition.  Now, “actionable data” can happen in real-time and will drive out holistic decision making.  Airports will leverage virtual twins to demonstrate how a change is modeled across the full life-cycle of the airport.   Upstream and downstream consequences will be more fully revealed and fewer “Gotchas” will happen. 

Making this shift to holistic and automated decision making is necessary to build and operate the airport of the 21^st century.  These new techniques will put passenger experience and innovation at the forefront.  Executives will be able to effectively initiate and deliver on top-down vision, goals, and service expectations with real data to back it up.         

Digital Twin Evolving to Virtual Twin

These new techniques will put passenger experience and innovation at the forefront.

Digital Twin technology and the application to an airport is an emerging topic and for good reason.  However, a virtual twin goes beyond the digital twin technology.  When incorporated as part of a platform environment, a virtual twin enables companies to create a consistent and comprehensive experience for all stakeholders, from design and construction through marketing, sales, operation and servicing.  Overall, it helps to better understand what is being delivered versus what was designed, tightening the loop between design and actual operation.  Simply stated, did it perform as designed?

For illustration, take an airport that exists in the physical world and equipped with sensors.  Now, this sensor data is incorporated with the airport’s 3D model’s layout of mechanical equipment, electrical and HVAC systems, simulation performance data, operational data, and everything else essential there is to know about the airport. Then real-world data interacts with the 3D model and updates it in real time. What you now have is a dynamic mirror of the airport: a Virtual twin. 

Now the Virtual twin could reveal insight into optimizing the airport’s performance. Such twins could simulate a day of operation and no real-world test required. In fact, Virtual twins are already being used for this purpose today—if they weren’t, physical autonomous vehicles would have to drive an estimated 14 billion kilometers to validate their performance.  An airport can optimize its performance and passenger journey by running many iterations based on real data in the virtual world before putting into operation.  Reduced risk, proven optimized designs, and higher confidence are the value propositions.

Embracing this new virtual twin technology will enable airports to achieve their innovation goals.  Fortunately, there are solid examples from other industries that can be leveraged.  

This article is the first of a series of articles on how to explore, develop, and adopt virtual twin technology to move the airport industry forward. Visit the DELMIA blog again to discover more!

Part 1 of a 2-part series

In recent years, machine learning is gaining more and more popularity, but what exactly is the Machine Learning? In this section, I will deep-dive so you will have a better understanding of what machine learning is, types and how machine learning is used.

Evolution of Machine Learning

The name “Machine Learning” initially originated from famous gaming researcher Arthur Lee Samuel. Samuel is the first person to bring self-learning programs into society. This remarkable discovery shortly laid the foundation for Machine Learning algorithms. In later years, raising popularity in Machine Learning (ML) and Artificial Intelligence (AI) give birth to many innovations in the field of Computers and Automation. Similar definitions and usage of ML & AI created ambiguity in distinguishing these two fields. In fact, few beginners in this field often use AI and Machine Learning interchangeably, but the fact is that they are the same.

Artificial Intelligence is the integration of Machine Learning algorithms. Artificial Intelligence models are used to perform multiple tasks such as self-driving cars, humanoid robots, etc.

On the other hand, Machine Learning is used to accomplish only specific tasks like spam detection, Movie recommendation, and Image classification.

Actually, Machine Learning is a sub-field of AI, the picture below clearly explains what I mean. 

Machine Learning is Broadly Segmented into 3 Types

1. Supervised Machine Learning
2. Unsupervised Machine Learning
3. Reinforcement Learning

Supervised Machine Learning

Supervised machine learning is the most commonly used technique. Many industries use supervised machine learning techniques to train machine learning algorithms.

In supervised Machine Learning, we supervise or teach the machine using labeled data. In other words, we show the sample data and tell the machine what the label is, likewise we do it for every sample in the data set.

Figure 1 explains the working of supervised Machine Learning.

In figure 1 Dataset consists of ‘n’ Labelled cat and dog images, each image is labeled with a tag. For instance, in figure 1 Image 1 is labeled as a cat. Likewise, there will be ‘n’ labeled images from 1 to n. 

In supervised learning, the teacher holds the actual values for every corresponding image in the dataset. Similarly, the learning system will give predicted values for every corresponding image in the dataset. Once we got the image output values from the teacher and learning system error function will calculate the error between actual and predicted values.

Using the feedback error, the learning system will keep on updating its parameters (weights) to minimize the error value. Eventually, this process of learning parameters (weights) will help the Learning system to understand the model.

Visit the DELMIA Blog again for Part 2 which will include details on Unsupervised Machine Learning and Reinforcement Learning. Meanwhile, you can connect with our DELMIA experts in the DELMIA Fabrication community for free. https://r1132100503382-eu1-3dswym.3dexperience.3ds.com/#community:45