Petecchi says carmakers ask Pirelli to develop a tire for a new car model about three years before the car launches.
“Car maker collasa to develop the tire for a new car three years in advance of the launch of a new car model.”
Person
Daniele Petecchi
1 episodes · 22 quoted claims
Petecchi says Pirelli sees a first replacement-tire wave four years after a car launches and a second wave four years after that.
“Then the new car model is launched. After four years, we have the first replacement wave. After four years again, we have the second wave of the replacement.”
Petecchi says the car development and replacement cycle gives Pirelli visibility of about eleven years.
“At the end, this provide us a visibility, this time frame of eleven years.”
Petecchi says Pirelli produces more than 60 to 70 million tires each year.
“let's go to consider that every year we produce more than sixty or seventy millions of tire.”
Petecchi says Pirelli makes its tires in eighteen plants worldwide and sells them in almost sixty markets.
“We produce this tire over eighteen plants around the world. We provide our tire of almost sixty market around the world.”
Petecchi says Pirelli produces roughly 2,000 to 3,000 different product variants (SKUs) each year.
“And to manage this complexity, because each year we produce two, 3,000 of different SKU.”
Petecchi says producing one tire takes about thirty minutes.
“the starting from the body, thirty minutes to produce one tire.”
Petecchi says tire design, especially the prototyping phase, used to take several months.
“Design process require, in particular for the prototyping phase, require several months in the past.”
Petecchi says tires are the only source of noise in an electric car because there is no engine noise.
“The only noise of an electric car is related to the tire.”
Pirelli trained a neural network model that can predict the noise of a tire.
“We trained our neural network and a neural network model, and we developed this kind of model that was able to predict the noise of the tire.”
Pirelli's deep-learning model predicts tire noise from the product design and technical parameters without building a prototype.
“We develop this kind of model, deep learning model, that are able to predict the noise of a tire based on the design of the product and other technical parameters without the prototyping phase.”
Petecchi says Pirelli's AI also suggests the recipe for a new tire according to customer requirements.
“we are able to predict not only the noise with the AI, we suggest also the proper recipe of our tire for a new product according to the customer requirements.”
Petecchi says Pirelli uses predictive maintenance and predictive quality in its production plants.
“And this is what we put in place with the predictive maintenance, predictive quality.”
Petecchi says Pirelli collects sensor (IoT) data from its machines to detect problems that could affect final product quality.
“So during the process, collecting the data with IoT data because we collect the data from our machine, our machine, we are able to detect if something is going wrong and could impact the end quality of our product”
Petecchi says a Pirelli tire uses more than one hundred ingredients and has twenty-six parts that are built and then cooked.
“Yeah, more than one hundred ingredients, and if you consider the tire, you have twenty six parts of the tire that are built and then cooked.”
Petecchi cites a Ferrari at 300 kilometers per hour as an example of the demands placed on a tire.
“if you consider that a tire has to support a car, and I don't know a Ferrari for 300 kilometers per hour of speed and temperature”
Petecchi says tires must cope with temperatures from about zero degrees in winter to forty or forty-five degrees in summer.
“So we can start in winter in Italy with a temperature that is, uh, zero degrees to forty or forty five degrees in summer.”
Petecchi says Pirelli began its data strategy and digital transformation in 2018.
“Here in Pirelli, we started in 2018, not only with the data strategy, data-driven approach”
Petecchi is an engineer trained in digital signal processing who began with university research on telecommunications data.
“My background is I'm an engineer, I'm an engineer in digital signal processing, and after the university, I support my professor in Italy for a few researches related to the data in telecommunication industry.”
Petecchi says AI at Pirelli splits into two mainstreams, one of which is operations built on deep learning.
“I can say the AI in Pirelli split in two mainstreams. One is the stream that I described before, the stream of the operation”
Petecchi says Pirelli mainly applies language-based generative AI in its staff functions.
“Gen AI, as I said today, by the hype of Chat GPT, is in particular applied for, as I said, the staff function.”
Petecchi argues the real problem is overselling, with ordinary calculations sometimes being marketed as AI.
“it's not too much AI, it's a bad marketing of AI. When you do something, there's, oh, this is AI.”