Advanced data analytics and machine learning will allow OEMs to analyze real data on how vehicles behave under specific driving circumstances, writes Ron Soreanu
Thirty days is June, the old saying goes. But in June 2022, automakers issued 31 recalls in the United States, averaging more than one a day. Recalls were carried out by nearly every foreign and domestic automaker – from Fiat-Chrysler to Hyundai to Porsche and Lamborghini – and individual recalls involved numbers ranging from 2.9 million vehicles to just one, for problems ranging from hardware integrity to software issues in vehicle computers. . It was just a typical month for automakers, which have been issuing recalls at the same rate for years now.
Is there a way out of this recurring recall dilemma? How is it that after building vehicles for nearly a century, automakers still aren’t succeeding? But a solution, or at least a partial solution, is emerging: modern technology in the form of artificial intelligence (AI) may in the future help manufacturers build better and safer vehicles, thereby reducing the probability of having to issue reminders. Using advanced data analytics and machine learning, OEMs will be able to analyze large amounts of real-world data on vehicle behavior in specific driving circumstances, taking into account the impact of weather, road conditions, driving habits, wear and other factors that may affect vehicle performance. Although there are many challenges, including production process adjustment and privacy issues, OEMs should take more steps to integrate this data into vehicle design and construction.
How is it that after building vehicles for nearly a century, automakers still aren’t succeeding?
The first step is to harness and use the big data collected by the plethora of sensors in modern vehicles, especially with the rise of connected autonomous and semi-autonomous vehicles. This, together with information about weather, traffic, the condition of the road itself, as well as data collected by repair shops on specific physical and operational issues, can offer valuable information about the operation and vehicle performance. This will allow manufacturers to better understand how to avoid issues that could lead to a recall. They could use this real-world data and information to help them design better parts or the best way to write or upgrade vehicle software. Eventually, automated production systems acting on data could rapidly change manufacturing processes to improve products rolling off the assembly line.
And while that’s a vision for the future – most cars haven’t yet fitted the advanced range of sensors needed for this sort of analysis – intelligent AI systems are already performing such predictive preventive analysis in a wide variety of fields, from medicine to machine repair. . OEMs, of course, already use some data for these purposes, but the advantage of advanced data analytics systems is that they can engage in machine learning, honing their knowledge of what makes a vehicle tick. – and what can prevent it from working – to build a model that OEMs can use to help eliminate problems.
It is already clear that data analysis works. In 2012, GM used a database that tracked parts used in its cars and collected manufacturing records from suppliers to track down a faulty part in some of its Chevy Volt models. As a result of the investigation, GM was able to avoid a mass recall—bringing in just four volts for service, to NHTSA approval. It took GM investigators a month to analyze the data to come to their conclusion – and in an era before the widespread deployment of sensors, apps and other sources of data collection, at a time when AI systems were less advanced than they are now. If GM was able to limit the recall a decade ago, current technology should be enough to prevent tens of thousands of vehicles from being recalled and save companies millions of dollars. And the data could be used to improve the manufacturing process, reducing the number of recalls overall.
But analyzing AI data to improve engineering and processes has yet to become the norm among OEMs. While manufacturers are already using AI in some production processes, OEMs have yet to put systems in place that can quickly act on data gathered from a large number of data sources, including connected car sensors, which would lead to interruption of the production process. So, alongside AI systems, OEMs should invest in automated systems to act on data and quickly pivot production processes to avoid production issues.
In addition to this logistical challenge, a McKinsey report attributes the slow adoption of AI analytics to several factors, including the traditional culture of the automotive manufacturing industry, where data is often siloed; Few, if any, OEMs have been able to develop dedicated cross-functional data monetization units that could effectively use AI-generated data to modify production and engineering systems. OEMs are also struggling to hire the talent needed for advanced data analytics and partnering with outside organizations, which is critical to getting the most out of data. Additionally, OEMs would need consumer permission, and many are simply not interested in disclosing data about their driving habits or vehicle condition.
Along with AI systems, OEMs should invest in automated systems to act on data and quickly pivot production processes to avoid production issues.
However, the data that OEMs could potentially collect is too valuable to ignore and once manufacturers develop the right methods to collect and use the data, they will be able to protect themselves from important issues and identify more quickly. design and mechanical issues that arise. . The data collected could include details of the condition of parts during vehicle maintenance as well as their condition after an accident or other incident. For example, if repair shops find that 60% of fender benders result in a broken passenger side mirror, this could indicate that the way the vehicle is built makes it more prone to such damage.
Manufacturers can also use this data-driven design approach to increase consumer confidence. Research shows that large or high-profile recalls not only hurt sales of a specific OEM nameplate, but even vehicles made by their competitors in the same country; a recall from Suzuki, for example, will also affect Subaru sales. By identifying problems and fixing them before a mass recall is necessary, OEMs can show consumers that their quality control is good enough to detect and fix problems before they get out of control. Additionally, it increases consumer brand confidence in the used car market, allaying lingering buyer concerns that dealers do not always return recalled cars to the manufacturer, but instead try to sell them as used vehicles.
Big Data has had a big impact on dozens of industries, and it’s time for OEMs to use Big Data to improve the manufacturing process, as well as increase consumer trust in their brands. Luckily for them, much of the data they need to analyze is already collected and used for various purposes; all they have to do is integrate it into the production process and put systems in place to quickly act on it. Why not use it to save yourself and consumers the trouble of having to deal with recalls and ultimately produce better and safer vehicles?
About the Author: Ron Soreanu is Vice President of Operations at Ravine AI
#Big #Data #OEMs #Build #Safer #Vehicles #Avoid #Recalls #automotive #world