Achieve electronic engineering efficiencies through ML and automation

A quiet but significant revolution is underway within the mass electronics industry. By leveraging machine learning (ML) and artificial intelligence (AI), companies in the industry are building new software that saves designers, engineers, distributors, and manufacturers time and resources, eliminating tired and analog work methods previously used to create electronic products, are gradually reduced .

ML and AI are more advanced than ever. But despite great strides, it’s surprising that a tech-savvy industry like electronics isn’t already leading the charge on automation. For example, printed circuit boards (PCBs), critical components in all electronic devices, are often still designed using the experiential knowledge and thought processes of human engineers. PCB design and manufacturing times remain archaically dependent on humans.

But a wind of change is blowing through the industry; ML begins to refine design processes. From improving searches for parts and components, to digitizing obsolete technical documents, to aiding design generation, ML illuminates insights about processes that would otherwise be invisible to engineers.

Assisting platforms

So what platforms are available to engineers to reduce PCB design process times, and what are their drawbacks and merits?

Let’s start with traditional ECAD (Electric Computer Aided Design) tools. These are complex software tools designed to enable engineers to perform any kind of detailed design (with some automation). However, they are usually geared only to manual technical work. Examples include Altium Designer, Siemens EDA, Cadence OrCAD, AutoDesk Eagle, and Zuken ECAD tools.

An alternative form of help that is widely used, but largely inefficient, is the office (or project) tool. Even today, engineers use office tools such as Excel, Atlassian, Visio and others to manage many of their activities, such as maintaining wikis and managing projects. Because they were never designed for day-to-day engineering work, these tools have multiple shortcomings and lack the specificity needed to save engineers time completing electronic designs.

Up-to-date information is crucial

Database providers also offer software tools that give engineers insight into component prices, availability and (some) technical specifications.

Up-to-date information about components and semiconductors is crucial in the electronics industry. However, this information can undermine or even negate engineers’ progress in product design because databases lack details about circuits and reference designs that are absolutely necessary to make compositional blueprints a manufacturable reality.

These three previous examples are all constituent platforms commonly used by engineers who, individually and collectively, fail to deliver informational and organizational coherence or time efficiency.

Therefore, there is a clear need to automate platforms, a new class of which has recently entered the market. Cloud-based platforms, focused on a high level of abstraction and functional design views, provide as much automation as possible and leverage the sharing and collaboration of different engineers. These platforms usually integrate seamlessly with existing design tools, such as traditional ECAD.

The power and dangers of data and the importance of machine learning

A pervasive topic of the digital age, not just in electronic engineering, is the evolution of ML and AI amidst abundant data flows. Technological capabilities for data storage, compilation, and comparison have expanded greatly in recent years and have thankfully reduced the time and resources engineers spend on projects. Despite this, handling data remains a difficult proposition as developers receive more and more information.

Without careful management and proper “hygiene” processes, more data can lead to more problems for those who struggle with it. New challenges arise from huge amounts of data, and especially bad data. For engineers, access to billions of data sets is useful to the point of information overload, which was all too common when PCBs were designed by hand, for example.

Data must be channeled in a way that makes ML suitable for use in electronic engineering. The future of industry, and technology more broadly, requires a focus on data quality. Data must be emphatically compressed to make it easily accessible and digestible. Users need clarity on which data points are essential and what to do with them. It will be up to data analysts to decipher the masses of data, with these roles attracting increasing investment from companies in the near future and beyond.

More flexibility, creativity

Within electrical engineering, the introduction of new data types also provides more flexibility and creativity. Not only can components be selected more quickly and functional designs can be created, other design features (such as sustainability) can also be woven into the final scheme.

Sustainable design selects components based on performance, recyclability and lifespan, leading to more appropriate procurement with new data streams becoming more prominent in the design phase.

Heralded by ML, the overall interest of healthier data management capabilities is the reduction of the learning curves required for the industry’s workforce and the ensuing effects of this. Ground-level tasks in PCB design that used to be performed by more skilled engineers are now being shifted to less experienced engineers using ML tools. This allows highly skilled designers to focus on more specialized tasks and helps companies with staff shortages, with ML picking up the slack.

Automation versus human input

The The main opportunity for AI and ML in electronic engineering is to remove errors from design and manufacturing processes. Using proven settings and designs from millions of users, errors are avoided and versatility is improved. Users can replace components and quickly adapt designs to market conditions and disruptions. AI and ML-enabled automation has been and will continue to revolutionize the industry in terms of design time efficiency.

But despite the rapid advance of automation technology, human input remains of the utmost importance. Questions about deploying this technology should not be about what we do can automate, but what we should automate. Creativity and innovation in design are not led by AI, but by skilled engineers. If we want to drive innovation in electronics, we will always need the human brain.

What needs to be automated are the manual and tedious tasks that waste engineers’ time (which could otherwise be spent on more important areas). Full automation is not the ultimate desired state, but it is the turbocharger that fires new efficiencies in electronic engineering.

Alexander Pohl is co-founder and CTO of CELUS.