Artificial Intelligence In Design :


 

1.INTRODUCTION:  

Artificial Intelligence and Machine Learning seems to be the current buzzword as everyone seems

to be getting into this subject. Artificial Intelligence seems to have a role in all fields of science. According to Britannica, “Artificial intelligence (AI), is broadly defined as the ability of a digital computer or computer-controlled robot to perform tasks commonly associated with intelligent beings.” By intelligent beings it basically means humans … but may be not all humans…so any way,

 

So, what does design bring to the conversation? With AI, new relationships will need to be established between customer and product. These interactions will be just the beginning of the ongoing conversation between business and consumer about what artificial intelligence can, and should be able to do for products and services. Designers will bring the necessary empathetic context for innovation, which is how a business will succeed with AI.




Rising Above the Hype

AI holds a lot of potential for the design world, but for this to happen the hype around it needs to be deconstructed. It would better if designers  cleared their minds and didn’t think about AI as “artificial intelligence”–as though AI was going to work as some kind of magic-tech. A more useful way to think about AI—at least for the short-term—is “augmented intelligence.

Robots are not replacing designers. IBM CEO Gini Rometty said  that “If I considered the initials AI, I would have preferred augmented intelligence.”

AI is going to be mostly about optimization and speed. Designers working with AI can create designs faster and more cheaply due to the increased speed and efficiency it offers. The power of AI will lie in the speed in which it can analyze vast amounts of data and suggest design adjustments. A design can then cherry-pick and approve adjustments based on that data. The most effective designs to test can be created expediently, and multiple prototype versions can be A/B tested with users. In this blog readers will get to know about how AI can be used in design by an example mentioned :


EVOLVING AN ANSWER

 

The generative design process may sound like something for the distant future, but recently it was applied to a real-world challenge involving a component for one of the most high-profile and expensive products in the world, the Airbus A320 aircraft. The part was a partition that separates the passenger compartment from the galley of the plane and supports a flip-down seat for flight attendants during takeoff and landing. Airbus engineers were looking for ways to reduce the partition's weight and volume while retaining enough strength to bear the loads of flight attendants. It also had to hold up under the force of 16 g in the event of a crash landing. A group of Airbus designers turned to Autodesk and other partners to see if they could come up with an improved partition through a combination of generative design, biomimicry concepts for material and structural design, and additive manufacturing. The generative design process the team used employed two algorithms derived from biological models. The first drew from the adaptive networks of slime mold: a single-celled organism that can grow, stretch, and aggregate to form multicellular structures, with the minimum number of lines. These structures have a built-in redundancy to retain connectivity within the network, in case a line fails. This algorithm was used to inform the design of the bracing for the overall partition. A second algorithm, derived from the microscale structure of mammal bones, was used to build the lattice that makes up each member. Several different load cases were considered, some requiring more than 66,000 micro-lattice bars in the partition. Once the design parameters were set, the generative design software (in this case Autodesk Within) cycled through thousands of design variants. The human design team digitally mapped the different generated options against weight, stress, and strength parameters to decide which to prototype. The resulting design is a latticed structure that looks random but is based on mammal bone growth. Like natural bone, the partition is dense at points of stress but lightweight everywhere else. The design, which Airbus and Autodesk call the bionic partition, is 45 percent lighter than the conventionally designed compartment divider found on existing aircraft. Fabricated using additive manufacturing, the finished product requires just one-twentieth the raw material compared with a partition built using traditional design processes.

 

THE AI CONTINUUM

 

Artificial intelligence is embedded in products ranging from smart gadgets and devices to drones, robots, and autonomous vehicles. Currently, the AI continuum can be divided into three general areas according to complexity:

 

ASSISTED INTELLIGENCE: AI automates basic repetitive and standardized tasks, working from clearly defined rules. Humans are still making the key decisions. Examples include automated assembly line robots as well as software-based agents that simulate the online activities of humans.

 

AUGMENTED INTELLIGENCE: AI enhances the ability of humans to accomplish tasks, and humans and machines learn from each other. Examples include intelligent virtual assistants, some of generative design systems, and systems that can bring unusual or noteworthy events to human attention.

 

AUTONOMOUS INTELLIGENCE: AI takes over some decision-making, but only after a human fully trusts the machine or becomes a liability to the prompt accomplishment of a task. Self-driving vehicles, currently in development by over 30 companies, are just one example of autonomous intelligence.

More than 100 separate pieces, made of a high-strength metal alloy developed by Airbus, were 3-D printed and then assembled. The resulting partition is the world's largest 3-D printed aircraft cabin component, and it more than satisfies the Airbus team's requirements. It is thinner and stronger than the component it will replace, and because it is 30 kg lighter, each bionic partition will save approximately 3,180 kg of fuel per plane per year. The partition is undergoing final testing and approval. Once complete, the final design could be used in A320 aircraft next year. The lessons Airbus learned in designing the bionic partition pave the way for changing how an entire aircraft is conceived and manufactured. The next generation of Airbus planes will be made up of components based on generative design, built by 3-D printing, using innovative materials. Airbus plans to evolve its methods for producing larger structures inside a plane: for example, the cockpit wall, which is twice the size of the bionic partition and needs to be bulletproof to protect the pilots, or the structure that houses the galley for food and beverage service.

 


AI used In Design of parts in Mechanical engineering :

 

We are going to talk about Deep learning methods and its possible role in the field of Mechanical Engineering. Some common examples could be Anomaly Detection (Machine Learning) and Image based Part Classification (Deep Learning). The focus will be on Image based part classifiers and why we need them.

Firstly, what is an image classifier? The ever famous AI which recognizes cat-dog pictures should come to mind. The data-set used contains images of cats and dogs, the algorithm learns from it and then is able to guess with 97% accuracy whether a randomly shown image is a cat or a dog.

We will attempt a similar code but using Nuts, Bolts, Washers and Locating Pins as our Cats and Dogs… because mechanical engineering.









So how does it work? An algorithm can classify images(efficiently) by using a Machine Learning algorithm called Convolutional Neural Networks (CNN) a method used in Deep Learning. We can a simple version of this model called Sequential to let our model distinguish the images into four classes Nuts, Bolts, Washers and Locating Pins. The model will learn by “observing” a set of training images. After learning we will see how accurately it can predict what an image (which it has not seen) is.






To create the model, we will have to follow 7 steps:

1.     Data Collection

2.     Data Preparation

3.     Model Selection

4.     Train Model

5.     Evaluate the Model

6.     Hyperparameter Tuning

7.     Make Predictions

 

 

 

AI used in CAD software /Quality Control Software /Manufacturing Software:


Artificial intelligence (AI) is a part of science that deals with study and development of the theory, technology and application systems for simulating and extending human intelligence, involving disciplines such as psychology, cognitive science, thinking science, information science, systems science and bioscience.

 

With the continuous progress of science and technology, mechanical engineering is also constantly evolving and changing, from the traditional mechanical engineering to the electronic-mechanical engineering. And attempts are being made by research to increase the level of automation and intelligence of a device. With development of AI, we see that most of the mechanical operation could be automatized and the accuracy and productivity of an operation could be increased with help of AI.

 

One of the traditional mechanical engineering processes is Designing & Drafting. What if this process could be assisted by a device with artificial intelligence? We use Computer Aided Designing (CAD) software to design and for drafting. Just imagine if AI could design with the data as simple as basic dimension, load carrying capacity, factor of safety etc., i.e., the basic requirement. Based on the input data a set of designs would be automatically generated and by selecting the most suitable designing we could proceed for analysis and then manufacturing process.

 

Basic workflow of AI based designing system, or a Generative Design system is:







  1.   Defining the rules of designing during development of AI based system. Entering basic requirements of desired product or object.
  2.  System then generates designs automatically based on the instruction and definitions seeded into the system.
  3.   Since the process is automated by AI it shows many possible solution i.e designs. Then the most suitable design is selected for fabrication.

 

AI improvements will directly affect our ability to be creative as engineers. Also, it increases our productivity and reduces drudgery to great extent. Therefore, it is important as an Mechanical Engineers to understand AI as it could help in many aspects of Mechanical Engineers apart from Designing, like Manufacturing, Metrology, Quality Assurance etc.


AI used Quality Control and Data-driven manufacturing (Renishaw) :

The foundation for all of AI systems will be data

Most manufacturers already have access to metrology data, but with the assistance of Renishaw Central, you can deploy that data consistently. Renishaw's portfolio of industrial metrology and additive manufacturing (AM) products, which can be used throughout manufacturing processes, provides the right data at the right time, enabling you to control your processes.​

The Renishaw Central manufacturing data platform provides a consistent method of connecting your Renishaw measurement and manufacturing devices, to make it easy for a variety of systems and processes to access Renishaw device data.​




Renishaw Central enables you to:

    • store and visualize your data
    • consume data into your digital systems
    • use standards-based connections

Connectivity

    • Automated efficient data collection.
    • Plug-and-play solution for easy implementation and maintenance.
    • Standards-based outputs allow connectivity to third-party platforms.
    • A single up-to-date view ​of factory data.

Control 

    • Continuous improvement through analysis of end-to-end process data across operations, cells and time periods.
    • Predict, identify and correct process errors before they happen by characterising acceptable process trends and performance.
    • Enhance understanding of process performance, part quality and product design by using metrology data captured throughout your processes.​


Consistency

    • Process automation for unattended 'lights out' productive manufacturing.
    • Intelligent and automated decision making requires less human intervention.
    • Use of data from multiple devices and operations for superior control of upstream processes.
    • Shorter feedback loops enable rapid reaction and adjustment to process variation.
    • Increase machine utilization and productivity while reducing scrap.

How it works

Renishaw Central provides consumers of Renishaw data with a storage and interface layer that contains up-to-date machine and job information, including metrology, machine status and alert data. This information is made available to customers in several ways, including standards-based output (such as MT Connect), the Renishaw Central API, and web browser visualization.

 

Conclusion:

Deep Learning (Artificial Intelligence) is a field of study that has immense possibilities as it enables us to extract a lot of knowledge from raw data. At its core it is merely data analysis. In this age of the internet, data is everywhere and if we are able to extract it efficiently, a lot can be accomplished.

This field has a lot of possible applications in the domain of Mechanical Engineering as well. Since almost all studies in Deep Learning need a domain expert it would be advisable for all engineers with interest in Data Analytics, even though they haven’t majored in Computer Sciences, to learn about data science, machine learning and examine its possibilities. The knowledge of the domain plus the skills of data analysis will really help us excel in our own fields.

 

 References:  

1.    Paper: Mechanical Product Lifecycle Management meets Product Line Engineering by Charles W. Krueger

2.    https://youtu.be/pJvG6dr1sQQ

3.    https://builtin.com/artificial-intelligence

4.    https://www.simplilearn.com/tutorials/artificial-intelligence-tutorial/artificial-intelligence-applications

5.    https://www.renishaw.com/en/data-driven-manufacturing--14152

6.    http://www.aee.odu








Comments