Quality during Design
Quality during Design is a podcast for product designers, engineers, and anyone else who cares about creating high-quality products. In each episode, we explore the principles of quality design, from user-centered thinking to iterative development. We introduce frameworks to make better design decisions and reduce costly re-designs. We explore ways to co-work with cross-functional teams. We also talk to experts in the field about their experiences and insights.
Join host Dianna Deeney in using quality thinking throughout the design process to create products others love, for less. Whether you're a seasoned designer or just starting out, looking to improve your existing designs or start from scratch, Quality during Design is the podcast for you.
Quality during Design
Predictive Analytics, Machine Learning, AI, and VR in Design Engineering
Discover how predictive analytics, machine learning, AI, and virtual reality reshape some of the ways we approach design. In this episode, we journey from the origins of predictive analytics to the convergence of big data, IoT, digital twins and more, paving the way for innovative product development. We'll also discuss the potential of virtual reality to enhance collaboration and communication within design processes.
This episode isn't just about embracing the latest tech trends; it's about knowing when simpler solutions will suffice and the critical role of data stewardship. This overview will help you to understand the big picture of where these tools fit into your design process. Listen-in so you can better choose when to use them to optimize your design engineering endeavors, or not.
Join the conversation by sharing your thoughts on our blog or newsletter.
Give us a Rating & Review
**NEW COURSE**
FMEA in Practice: from Plan to Risk-Based Decision Making is enrolling students now. Visit the course page for more information and to sign up today! Click Here
**FREE RESOURCES**
Quality during Design engineering and new product development is actionable. It's also a mindset. Subscribe for consistency, inspiration, and ideas at www.qualityduringdesign.com.
About me
Dianna Deeney helps product designers work with their cross-functional team to reduce concept design time and increase product success, using quality and reliability methods.
She consults with businesses to incorporate quality within their product development processes. She also coaches individuals in using Quality during Design for their projects.
She founded Quality during Design through her company Deeney Enterprises, LLC. Her vision is a world of products that are easy to use, dependable, and safe – possible by using Quality during Design engineering and product development.
Predictive analytics, machine learning, ai and virtual reality in design engineering. Am I really going to try to cover all of this in a 15-20 minute podcast episode? Yes, I am. As design engineers, we want to use technology in a smart way to help us. However, there's no need to overcomplicate things. We don't need to use AI to generate a normal probability plot, for example. There are so many options and tools. Where do we even start to determine what it is we need? Sometimes, starting with methods that have been around for a while is all that we need. Other times, we need to push past what we've done before and try a new technique. The first step is knowing what's available and why it matters to engineering decisions. So let's talk about all the things after this brief introduction. Hello and welcome to Quality During Design, the place to use quality thinking to create products. Others love for less. I'm your host, diana Deeney. I'm a senior-level quality professional and engineer with over 20 years of experience in manufacturing and design. I consult with businesses and coach individuals on how to apply quality during design to their processes. Listen in and then join us. Visit qualityduringdesigncom.
Dianna Deeney:Today, we're exploring predictive analytics, machine learning, artificial intelligence and virtual reality, and we're exploring how these technologies intersect and are used in design engineering. We had a friend over for dinner on Sunday night and my husband got out his virtual reality headset. Our friend's family was traveling to Europe and he was able to use a worldview virtual reality and figure out where it is. His family was sightseeing in Europe. It was like he was hovering in a helicopter, except he was just hanging out in space and looking down on the world. We played around with the VR set with a few more other things, but the topic came up of practical uses for virtual reality and I was describing to them how some engineers are using virtual reality to communicate ideas and to make design decisions. And that leads to thoughts about AI, because everybody's talking about AI right now.
Dianna Deeney:As excited as I get about these new ways of doing things, I think we need to be smart about it. Just because we can doesn't mean it's worth doing. In design engineering, we really want to use these tools for many reasons. One is we want more efficient and effective designs. We want to optimize our designs. We want to be able to make decisions with data-driven insights. We want to enhance our collaboration and improve our teamwork. We want faster product development cycles. We want to get our product to the market in an accelerated way and, last but not least, we want to increase our product quality. We want to reduce the defects and improve our product performance in the field. With these goals, if we understand the unique strengths of each of these technologies and if we understand how they can be combined, we can leverage these tools to be able to create those innovative and high-quality products that we want to create. I want to approach all these topics from a development timeline as far as who was doing what, when and how they were doing it, because they all build upon each other to sort of a crescendo at where we are today with all of these available tools.
Dianna Deeney:My background is mechanical engineering and medical devices, and I found myself in quality engineering and doing reliability engineering work also. So the first topic that comes to mind when I think of all these kind of tools is the predictive analytics, because that's what I was using earlier on in my career. I was using predictive analytics. So what is predictive analytics? It's analyzing data to be able to predict what happens next. It's used in risk assessment, so we're identifying potential risks in our design and manufacturing processes and then deciding to manage them or control them, to manage them or control them. Predictive analytics is also used for failure analysis, where we're analyzing historical data to predict potential failures. This historical data could be field data. It could be data that we designed to collect, in the case of accelerated life testing, for example. It can be used for predictive maintenance and this helps you determine if there's any proactive maintenance that you need to do, like replacing components before they fail.
Dianna Deeney:If you think of statistical modeling, that's an early form of predictive analytics and it relied on statistical models. That was the early stages of predictive analytics and if you're looking at a timeline, we can sort of place that in the 1950s to the 1980s. Then in the 1990s computers became more readily available and used more often. So then we got into advanced statistical techniques like Weibull analysis. We started data mining to extract patterns and insights from large data sets and we started doing a lot of simulation and modeling. Two prime examples of this is finite element analysis and computational fluid dynamics. So predictive analytics is where it all started and it's here to stay, because machine learning and predictive analytics are often used together to build predictive models and forecast future trends. So let's take a closer look at machine learning Machine learning. In our timeline, we could look at it as starting around the 2010s. Until now, we're still using it.
Dianna Deeney:When I think of machine learning, I think of those vision systems that are used on manufacturing production lines, where it's used as part of quality control. Where a camera is identifying defects on a product using image recognition is identifying defects on a product. Using image recognition, it can be used in simulations so that we can optimize the variables in those simulations. With machine learning, we are not explicitly programming anything. Instead, we're using algorithms to allow computers to learn from data. It involves training models on large data sets to be able to recognize patterns so that we can make predictions. Some of the ways that we do this training is through supervised learning, unsupervised learning, reinforcement learning and neural networks and deep learning.
Dianna Deeney:One of the things that necessitates machine learning is a very large data set, and that involves big data. We are living in the big data era, which involves machine learning. It also involves the Internet of Things devices, which are generating massive amounts of data that we can use in machine learning to provide valuable insights for predictive analytics. Another technique that generates a lot of data is digital twins. Digital twins can collect real-time data from physical assets, or they can generate synthetic data through simulations. Another source of a lot of data that you may have heard of is a digital thread. That's essentially a digital representation of a product's life cycle, from design to manufacturing to service, and it connects various stages of the product life cycle through a flow of data. All of that data can be used within machine learning for predictive analytics, and this brings us to artificial intelligence.
Dianna Deeney:Machine learning is a subset of AI, and many AI applications rely on machine learning techniques. However, just because it's an AI doesn't mean that it is using machine learning techniques. Here's some of the biggest differences AI that uses machine learning techniques heavily relies on data, on large amounts of data, in order to learn patterns, and we teach it through those learning processes that I just described. The AI that uses machine learning techniques can handle complex tasks like image and speech recognition, and it can adapt to new data and improve performance over time. The AI that uses non-machine learning techniques is less reliant on data and more reliant on knowledge bases and rules. It doesn't learn from data, but it relies on programming and those rules, so it's less adaptable. It requires manual updates to the rules and the knowledge bases, and it's right now often limited to simpler tasks or well-defined problems. Search algorithms are a non-machine learning technique, whereas neural networks and decision trees are a machine learning technique. If we continue down the trail of predictive analytics to machine learning, to AI in this case, ai is really helping us to optimize our activities, to make it simpler to sort through data, to get information, to make decisions. When we start talking about self-driving cars and other autonomous systems, ai and machine learning are together driving the development of those systems. Ai and machine learning are together driving the development of those systems and I think that would require a whole other podcast episode.
Dianna Deeney:Now, if you remember, at the top of the episode I talked about having a friend over for dinner and trying out the VR. Well, now we've come full circle. The VR kind of started this whole thing and now we're going to end with the virtual reality experience In product design. Virtual reality is another mode of communication and another mode of analysis. We can help our teammates have that immersive experience with our product without being able to physically tangibly touch it. Within a 3D world, they could move things around and interact with our product ideas. This could help us to more easily collaborate with our teammates on the product designs that we're doing. It's also another mode of prototyping, because now, instead of creating a physical prototype, we can look at a virtual prototype. That may help us reduce costs and accelerate our time to market. Some people are using the virtual reality 3D models to test product ergonomics. As of right now, I think you really have to evaluate whether or not the immersive 3D experience is going to get you the feedback that you need from your customers and your teammates in order to help you make design decisions. Even though it's a virtual model and it doesn't cost us in physical materials, there is a lot of other time and resources invested in creating a 3D model.
Dianna Deeney:How does virtual reality, ai and machine learning intersect? Well, ai and machine learning can be used to enhance the virtual reality experiences, like generating a realistic virtual environment or providing intelligent interactions. So that is a Cliff Notes version of all these tools for design. Engineering, predictive analytics, machine learning, ai and virtual reality are all tools that are mostly available for us to use, or at least an option that we might want to consider when we're doing product design. After this overview of these tools, what's the insight to action here? I think it's to always go back to what it is. You want to learn. What is this tool helping you to decide?
Dianna Deeney:In one of the Speaking of Reliability podcast episodes, fred Schenkelberg told a story about an engineer that showed him that he was excited. He created an SPC chart using artificial intelligence and Fred's response was why? What's the value in that? Because with a statistical process control chart, you really want to map it out real time to decide if you need to adjust something, not to collect the data and then generate a plot. The other thing is a statistical process control chart you can draw by hand. You don't need to use AI to do it.
Dianna Deeney:With these tools, it's not like learning a new program language.
Dianna Deeney:If you were of my generation or if you learned coding, you know that you started to code with simple tasks and simple outputs in order to better understand how to code and how the program worked.
Dianna Deeney:With these kind of tools, we don't need to start so simply, but we do want to have a basic understanding of them. Even though we have machine learning and AI and virtual reality, there is still a place for the basics of predictive analytics and mocked up prototypes. But having a basic understanding of predictive analytics and then machine learning with big data will help us to understand and decide if these new tools are worth it or if it's overkill, if we need to go back to the simpler predictive analytics and decide that that's really all we need. No matter what, we need to be good stewards of data. We need to be able to understand how to collect, clean and analyze data so that we can extract valuable insights for our design decisions.
Dianna Deeney:If you have anything to share about these four different topics predictive analytics, machine learning, ai and virtual reality leave a comment on this podcast blog at qualityduringdesigncom or, if you're subscribed to the monthly newsletter, just respond to the email from which the newsletter is sent. Your message will be sent directly to my inbox. I hope this overview has helped you peg and place these different technologies within your world of design engineering. This has been a production of Dini Enterprises. Thanks for listening.
