Data is Key in Digital Transformation of Process Industry
Published on : Thursday 01-06-2023
Endress+Hauser harnesses data and artificial intelligence to optimise internal processes along the value chain.
But only rarely does data find its way beyond the confines of the devices, machinery and systems that generate it. Now that could all change, thanks to smart field instrumentation, digital interfaces and cloud-based analytical tools. The possibilities are endless, particularly when sensors in the physical world are linked up to artificial intelligence.
Industry at a turning point
And yet there are areas of industry where change is afoot, says Birkhofer. The latest generation of smart instruments can supply a wealth of supplementary data alongside their actual measurements, including information on the sensors and processes themselves. There are technologies that provide a secondary channel for rapid, secure data transfer from the field right up to the corporate level that is completely distinct from process control in the plant itself. Furthermore, a host of projects have already demonstrated how this data can be turned into useful information and valuable knowledge. “Digitalising process plants is beginning to emerge more and more from the confines of pilot installations and small-scale projects,” Birkhofer says. And, he adds with conviction, “We are at a turning point.” For plant operators, it’s all about efficiency, security, and quality in the face of competitive pressure and a general shortage of skilled workers. It follows that there is an enormous number of potential use cases. Analysing data at the level of individual measuring points can already bring significant benefits. But the data generated from instruments and processes only reveals its true value after central aggregation, be that in a cloud application or edge computing system. Aggregation brings scalability to data gathering and processing, with individual use cases no longer requiring their own dedicated software. A further possibility is to link data from the field with other data sources such as weather forecasts and ERP systems, all in real time.
Virtual & physical world
A particularly exciting prospect is to combine multiple data sources using artificial intelligence. “Big data applications can glean highly complex insights in fractions of a second, given the right data inputs,” says Florian Falger, Market Manager at the Endress+Hauser Level+Pressure Innovation Lab. One of the team’s activities is finding ways to precisely determine maintenance intervals for measuring instruments and entire plants with the help of specialised algorithms and artificial intelligence. Thus, they are laying foundations for something that many companies in the process industry want: predictive maintenance. “Large chemical plants, for example, operate around the clock,” Falger explains. “Even planned maintenance is a costly undertaking. Predictive maintenance would help to minimise the plant downtime involved and avoid unscheduled outages, as well as reduce workload and costs.”
A clear advantage
Endress+Hauser harnesses data and artificial intelligence to optimise internal processes along the value chain. The result is improved transparency, quality, and efficiency – for customers, too. Here are five examples.
Easier interaction
Shopping like Amazon, searching like Google: endress.com is Endress+Hauser’s online platform for cooperation with customers. “To continue improving our website, we collect information about users’ surfing and purchasing behaviour,” explains Vincent Dessus, Head of Digital Business Development at Endress+Hauser. The company uses this data to make it easier for customers to find, select and order the right devices for their needs. An algorithm uses initial entries made in the device configuration, along with user location data, to determine the product typically ordered by customers there. Then it automatically fills in the next few fields. There is also a new ‘Get quote’ feature: “We noticed that although online customers don’t expect an individual quote, they do still need an official document,” says Vincent Dessus. “Now they can get a PDF quote in seconds.”
Smart production
Artificial intelligence supports laser welding in pressure transmitter production. “Conventional algorithms don’t reliably recognise the welding position,” says AI expert Dr Jawad Tayyub from Endress+Hauser Level+Pressure. “That means the people at the welding stations must check it every time. They often must make corrections manually, which is monotonous and tiring work.” Artificial intelligence immediately increases the correct detection rate to over 98 per cent, making work easier and reducing the number of rejects. “We do that using a neural network taken from the medical sector,” Tayyub explains. A comparable network helps doctors to detect skin cancer. The raw data is similar in both cases: image analysis largely concerns monochromatic areas that clearly stand out against their surroundings.
Optimised shipping
Endress+Hauser does not keep a stock of measurement devices. Given the multitude of variants, almost every instrument is one of a kind and made to order. Many regions handle shipping from a central logistics hub. “At our North American and European hubs, an algorithm ensures that products reach the customer on time. The AI is flexible to find the best logistics service for each delivery based on historical and current data,” explains Oliver Blum, Corporate Director of Supply Chain. The algorithm ensures the deliveries are reliable, even in unsettled times: in 2021, 91.2 per cent of deliveries in Europe arrived on time.
Proactive service
What is the long-term performance of measuring instruments in the field? Endress+Hauser introduced a specialised web application several years ago to find out. “An overnight database run condenses every service case worldwide into a single graphic, so we can see at a glance whether there are frequent events with a particular device,” explains Enrico De Stasio, Head of Lean Administration. These reports are used to identify the cases in question, since sometimes all that is needed is a routine service. “This lets us service or recall the devices in good time – before our customers experience any issues,” De Stasio says. The data also helps with new developments and with detailed understanding of the root causes of instrument damage: “Often, environmental conditions at the installation site are a factor in servicing,” adds Thomas Fricke, Head of Marketing Services at Endress+Hauser Temperature+System Products. Plans are under way to improve the application by using AI and integrating other sources such as m
Transparent purchasing
The Endress+Hauser Group has over 50 sales centres. As well as selling products, they increasingly offer solutions and services. This involves sourcing materials, such as mechanical accessories, and expertise from third parties. “To add transparency and structure in this area, an AI application scans through texts from all our SAP systems and assigns the third-party items to merchandise categories. It would take months for humans to analyse and interpret these tables,” says Oliver Blum. The AI system was trained by employees, and the sales team is working on enhancing the data quality. “This means we can now pool our purchasing activities and increase quality for customers,” Blum adds.
Source: https://changes.endress.com/sites/default/files/2023-05/E%2BH_22_002_changes2-22_EN_Web_221018.pdf
